© 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. 26580
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes related to hyperlinks and reports

    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
    +0.17
    0.8%
    703
    +0.13
    0.6%
    142
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.17
    0.01
    321
    +0.13
    0.01
    451
    +0.12
    0.01
    Negative Logits
    xxx
    -1.08
    found
    -1.07
    nik
    -1.07
    express
    -1.04
    conv
    -1.04
    closed
    -1.02
    advertisement
    -1.02
    fold
    -1.00
    pend
    -1.00
    andro
    -1.00
    POSITIVE LOGITS
     Traffic
    0.80
     Menu
    0.79
     Hour
    0.77
     Achievements
    0.75
     Mission
    0.75
     Title
    0.75
     Campus
    0.74
     Moment
    0.74
     Activity
    0.74
     Toggle
    0.72
    Activations Density 0.072%

    No Known Activations