© 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. 5203
    Prev
    Next
    INDEX
    Explanations

    references to transitions or connections between ideas

    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
    715
    +0.14
    0.7%
    373
    +0.09
    0.4%
    88
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.05
    172
    +0.09
    0.03
    715
    +0.09
    0.04
    Negative Logits
    cats
    -0.64
    ridge
    -0.63
     intimidated
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.60
    ourn
    -0.59
    alse
    -0.59
     taste
    -0.59
    ellig
    -0.58
     endors
    -0.58
    aughs
    -0.56
    POSITIVE LOGITS
     Conclusion
    0.85
     WHY
    0.84
     why
    0.82
    âĢ¦)
    0.81
    âĢ¦]
    0.80
     QUEST
    0.79
    why
    0.79
     question
    0.75
    ...)
    0.75
    cue
    0.71
    Activations Density 0.481%

    No Known Activations