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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4747
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between subjects or entities

    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
    373
    +0.17
    0.8%
    674
    +0.12
    0.5%
    339
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.17
    0.08
    362
    +0.12
    0.09
    703
    +0.10
    0.05
    Negative Logits
    omever
    -0.76
     assum
    -0.69
    nown
    -0.68
     whereas
    -0.68
     respectively
    -0.67
     thereof
    -0.67
     whichever
    -0.66
    Footnote
    -0.64
    .""
    -0.63
    printf
    -0.63
    POSITIVE LOGITS
     Shutterstock
    0.96
     Timeline
    0.86
     nutshell
    0.84
     Various
    0.81
     Miscellaneous
    0.81
     Edit
    0.78
     Overview
    0.77
     Conclusion
    0.75
     Photograph
    0.75
     Photos
    0.73
    Activations Density 1.034%

    No Known Activations