© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 7175
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.13
    0.6%
    447
    +0.12
    0.6%
    64
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.13
    0.10
    6
    +0.12
    0.10
    314
    +0.11
    0.01
    Negative Logits
     sailing
    -0.70
     acting
    -0.68
     incoming
    -0.66
    fired
    -0.65
     poisoning
    -0.65
     speeding
    -0.64
     directing
    -0.63
    ocamp
    -0.63
    stown
    -0.63
     burning
    -0.63
    POSITIVE LOGITS
    ================================================================
    1.23
    --------------------------------------------------------
    1.17
    ----------------------------------------------------------------
    1.15
    NOTE
    1.15
    ================
    1.08
    APTER
    1.07
    =-=-=-=-=-=-=-=-
    1.05
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    1.05
    ------------------------------------------------
    1.03
    ================================
    1.02
    Activations Density 0.593%

    No Known Activations