© 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. 5204
    Prev
    Next
    INDEX
    Explanations

    questions that express confusion or challenge the status quo

    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
    620
    +0.12
    0.5%
    314
    +0.10
    0.5%
    186
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.12
    0.04
    628
    +0.10
    0.04
    572
    +0.10
    0.04
    Negative Logits
     successive
    -0.84
     selective
    -0.71
     sustained
    -0.67
     environmental
    -0.66
    etheless
    -0.66
     continued
    -0.64
     gradual
    -0.63
     delays
    -0.62
     surplus
    -0.62
     fewer
    -0.62
    POSITIVE LOGITS
    fuck
    0.89
    soType
    0.88
    abouts
    0.79
    ãĤ§
    0.78
    isSpecialOrderable
    0.78
    fork
    0.75
     ;)
    0.74
    Fuck
    0.73
    Ñı
    0.73
    bang
    0.72
    Activations Density 0.195%

    No Known Activations