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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5391
    Prev
    Next
    INDEX
    Explanations

    references to international organizations or entities

    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
    267
    +0.14
    0.6%
    308
    +0.13
    0.6%
    12
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.14
    0.04
    267
    +0.13
    0.03
    498
    +0.12
    0.03
    Negative Logits
    boards
    -0.78
    yard
    -0.77
    yards
    -0.76
    board
    -0.76
    wick
    -0.74
    rooms
    -0.72
    backs
    -0.70
    lot
    -0.70
    rils
    -0.69
     trough
    -0.66
    POSITIVE LOGITS
     Monetary
    0.88
     Brotherhood
    0.87
     Speedway
    0.84
     Federation
    0.83
     Airport
    0.83
     Cooperation
    0.82
     Rac
    0.79
     Version
    0.77
     Exhibition
    0.76
     Classification
    0.76
    Activations Density 0.057%

    No Known Activations