© 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 EvalsExportsAPI 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. 31096
    Prev
    Next
    INDEX
    Explanations

    references to girls 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
    383
    +0.13
    0.6%
    274
    +0.09
    0.4%
    247
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.13
    0.03
    235
    +0.09
    0.02
    485
    +0.09
    0.02
    Negative Logits
    rehend
    -0.82
    ktop
    -0.79
    arily
    -0.79
    psey
    -0.77
    nce
    -0.75
     Canaver
    -0.73
    utherford
    -0.72
    rehens
    -0.71
    erate
    -0.71
    glas
    -0.70
    POSITIVE LOGITS
     Scouts
    1.01
    folk
    1.00
    girls
    0.97
     girls
    0.90
     aged
    0.89
    girl
    0.85
     scouts
    0.84
    agers
    0.83
     ages
    0.82
     panties
    0.82
    Activations Density 0.069%

    No Known Activations