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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31361
    Prev
    Next
    INDEX
    Explanations

    references to testing in programming and software development

    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
    314
    +0.09
    0.4%
    72
    +0.09
    0.4%
    317
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.09
    0.04
    255
    +0.09
    0.04
    288
    +0.08
    0.04
    Negative Logits
    soType
    -0.73
     Warfare
    -0.69
    adian
    -0.67
     violet
    -0.67
     adolescence
    -0.63
     aft
    -0.60
    ols
    -0.60
     appell
    -0.59
     Rouge
    -0.59
     revolutionary
    -0.58
    POSITIVE LOGITS
     suite
    1.23
     suites
    1.20
    su
    1.11
    udo
    0.97
    dir
    0.96
    bench
    0.93
     Suite
    0.93
    Su
    0.90
    script
    0.84
    cli
    0.82
    Activations Density 0.299%

    No Known Activations