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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4466
    Prev
    Next
    INDEX
    Explanations

    references to video games and related terminology

    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
    431
    +0.12
    0.6%
    1
    +0.10
    0.5%
    521
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.12
    0.04
    227
    +0.10
    0.03
    153
    +0.10
    0.06
    Negative Logits
     Emin
    -0.98
     stub
    -0.75
     Merrill
    -0.73
     divid
    -0.71
     ital
    -0.70
    rils
    -0.69
     expans
    -0.68
     pt
    -0.67
     redund
    -0.67
     shy
    -0.67
    POSITIVE LOGITS
     bicycle
    0.97
     motorcycle
    0.94
     automobile
    0.93
    bike
    0.85
     automotive
    0.85
     bike
    0.84
     gaming
    0.84
     Boat
    0.83
     railway
    0.82
     Football
    0.81
    Activations Density 3.787%

    No Known Activations