© 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. 10-RES_POST_32K-OAI
    11. 27465
    Prev
    Next
    INDEX
    Explanations

    imperative or essential language, indicating recommendations or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    176
    +0.10
    0.5%
    620
    +0.10
    0.4%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.02
    620
    +0.10
    0.01
    339
    +0.09
    0.01
    Negative Logits
    é¾
    -0.71
    é¾įå¥ij士
    -0.70
    é¾įåĸļ士
    -0.68
    theless
    -0.67
    issance
    -0.64
    GGGGGGGG
    -0.64
     æľ
    -0.60
    iency
    -0.59
    REDACTED
    -0.59
     FINAL
    -0.59
    POSITIVE LOGITS
    ache
    1.13
    angs
    0.97
    ard
    0.93
    ached
    0.88
    reads
    0.86
    ained
    0.84
    ang
    0.83
    ach
    0.82
    aining
    0.82
    opic
    0.81
    Activations Density 0.122%

    No Known Activations