© 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. 27404
    Prev
    Next
    INDEX
    Explanations

    the word "do" and its variations in various contexts

    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
    736
    +0.11
    0.5%
    690
    +0.11
    0.5%
    455
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.11
    0.05
    70
    +0.11
    0.06
    588
    +0.10
    0.06
    Negative Logits
    roid
    -0.79
     EDITION
    -0.60
     adore
    -0.56
    Ocean
    -0.55
    mares
    -0.55
    PLA
    -0.55
     hoard
    -0.54
    lights
    -0.53
     Doodle
    -0.52
     Falk
    -0.52
    POSITIVE LOGITS
    business
    0.96
     otherwise
    0.93
     business
    0.89
     justice
    0.87
     anything
    0.80
    ief
    0.73
    something
    0.71
     Business
    0.71
    acea
    0.71
    oldown
    0.71
    Activations Density 0.346%

    No Known Activations