© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4343
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that indicate significant statements or conclusions

    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
    610
    +0.10
    0.4%
    586
    +0.09
    0.4%
    235
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.21
    6
    +0.09
    0.21
    107
    +0.09
    0.12
    Negative Logits
    iquette
    -0.85
    resent
    -0.79
     Corinth
    -0.75
     Casual
    -0.74
    Street
    -0.73
     Accord
    -0.72
     casualty
    -0.71
     Charter
    -0.70
     condos
    -0.69
    street
    -0.68
    POSITIVE LOGITS
     scientists
    1.43
    Scientists
    1.38
     Scientists
    1.32
    Researchers
    1.27
     researchers
    1.25
     Researchers
    1.22
     physicists
    1.19
     biologists
    1.18
    Explore
    1.17
    scient
    1.16
    Activations Density 1.892%

    No Known Activations