© 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. 8-RES_POST_32K-OAI
    11. 7171
    Prev
    Next
    INDEX
    Explanations

    references to age, particularly concerning young children

    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
    433
    +0.12
    0.5%
    459
    +0.10
    0.5%
    741
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.12
    0.03
    433
    +0.10
    0.03
    153
    +0.10
    0.03
    Negative Logits
    recated
    -0.79
    pmwiki
    -0.74
     Canaver
    -0.72
    icist
    -0.66
    ioxide
    -0.65
    chwitz
    -0.64
    Prof
    -0.64
    kefeller
    -0.64
    ivery
    -0.63
     fug
    -0.62
    POSITIVE LOGITS
     daughter
    1.06
     boy
    1.06
     boys
    1.03
     girls
    1.02
     girl
    0.99
     daughters
    0.98
     son
    0.92
     children
    0.91
     kindergarten
    0.89
     kids
    0.86
    Activations Density 0.111%

    No Known Activations