© 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. 10-RES_POST_32K-OAI
    11. 32700
    Prev
    Next
    INDEX
    Explanations

    technical terms related to web browser functionality and multimedia support

    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
    373
    +0.12
    0.6%
    78
    +0.11
    0.5%
    188
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.01
    521
    +0.11
    0.01
    470
    +0.11
    0.01
    Negative Logits
     Instruct
    -0.76
     numbered
    -0.71
     manifold
    -0.67
     subtract
    -0.64
     neb
    -0.63
     Volunte
    -0.62
    rm
    -0.61
     Encounter
    -0.61
     Haz
    -0.60
     misunder
    -0.59
    POSITIVE LOGITS
    iframe
    0.94
    allow
    0.78
    embed
    0.71
     JavaScript
    0.71
    Allow
    0.67
     Ads
    0.65
     ads
    0.65
     javascript
    0.63
     browser
    0.63
    js
    0.63
    Activations Density 0.270%

    No Known Activations