© 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. 27200
    Prev
    Next
    INDEX
    Explanations

    words starting with "cl" and "pl" and patterns related to templates and classifications

    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
    582
    +0.11
    0.5%
    696
    +0.10
    0.5%
    314
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.00
    514
    +0.10
    0.04
    439
    +0.10
    0.04
    Negative Logits
     neglected
    -0.62
    older
    -0.60
     Gut
    -0.57
     includ
    -0.57
     psychiat
    -0.57
     skelet
    -0.56
     fright
    -0.56
     misunder
    -0.56
    mma
    -0.55
     Booth
    -0.54
    POSITIVE LOGITS
    ature
    1.21
    atures
    1.02
    eness
    1.02
    ify
    1.00
    ified
    0.99
    ifier
    0.87
    ength
    0.83
    ifying
    0.83
    ety
    0.82
    ée
    0.82
    Activations Density 0.438%

    No Known Activations