© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5246
    Prev
    Next
    INDEX
    Explanations

    terms related to penetration or the act of entering or influencing something

    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
    183
    +0.12
    0.6%
    710
    +0.10
    0.5%
    571
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.03
    332
    +0.10
    0.02
    326
    +0.10
    0.02
    Negative Logits
    corn
    -0.75
    arb
    -0.73
    makers
    -0.67
     Tycoon
    -0.65
    HCR
    -0.65
    umble
    -0.64
    ULE
    -0.63
    ark
    -0.63
     Malf
    -0.63
    ÄŁ
    -0.61
    POSITIVE LOGITS
     penetrated
    1.21
     penetration
    1.21
     penetrate
    1.09
     penet
    1.08
     penetrating
    0.96
     deeper
    0.86
     deepest
    0.78
     pierced
    0.77
     piercing
    0.75
    ierce
    0.75
    Activations Density 0.151%

    No Known Activations