© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 4881
    Prev
    Next
    INDEX
    Explanations

    instances of the word "for" and its frequency in various contexts

    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
    314
    +0.14
    0.6%
    373
    +0.13
    0.6%
    441
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.03
    322
    +0.13
    0.03
    570
    +0.10
    0.01
    Negative Logits
     Tribunal
    -0.72
    ERAL
    -0.67
    xual
    -0.65
     foresee
    -0.64
    phalt
    -0.64
     Flask
    -0.62
     poker
    -0.61
     evenings
    -0.60
     Residential
    -0.59
     dab
    -0.58
    POSITIVE LOGITS
    aldo
    0.70
    angs
    0.69
    iji
    0.67
    iar
    0.67
     touchdowns
    0.67
    161
    0.67
    utan
    0.65
    ang
    0.65
    kamp
    0.65
    obb
    0.65
    Activations Density 0.213%

    No Known Activations