© 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. 27900
    Prev
    Next
    INDEX
    Explanations

    frequent mentions of code or file-related terms

    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
    555
    +0.10
    0.4%
    673
    +0.10
    0.4%
    252
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.03
    326
    +0.10
    0.03
    153
    +0.10
    0.02
    Negative Logits
    xual
    -0.77
    fman
    -0.70
     messenger
    -0.67
    iard
    -0.65
     Fas
    -0.61
     tremend
    -0.59
     denomin
    -0.59
     partName
    -0.58
    CLASSIFIED
    -0.58
    soever
    -0.57
    POSITIVE LOGITS
    natureconservancy
    0.74
    ornia
    0.69
    ritz
    0.68
    uten
    0.66
    orno
    0.66
    orn
    0.66
    za
    0.63
    ruits
    0.62
    DS
    0.62
    efe
    0.61
    Activations Density 0.485%

    No Known Activations