© 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. 7952
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation marks in the document

    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
    678
    +0.12
    0.5%
    717
    +0.11
    0.5%
    374
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.12
    0.10
    720
    +0.11
    0.12
    546
    +0.10
    0.09
    Negative Logits
    heim
    -0.76
    ylum
    -0.71
    profit
    -0.70
    gression
    -0.70
     Inher
    -0.68
     Founding
    -0.68
    icated
    -0.68
    ontent
    -0.68
     Else
    -0.67
     Founders
    -0.66
    POSITIVE LOGITS
     palms
    0.98
     elbows
    0.89
     toes
    0.85
     spraying
    0.84
     paddle
    0.84
     puff
    0.83
     elong
    0.82
     flatt
    0.79
     cheeks
    0.79
     blinking
    0.78
    Activations Density 0.814%

    No Known Activations