© 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. 32270
    Prev
    Next
    INDEX
    Explanations

    numerical values related to scores or points

    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
    +0.17
    0.8%
    326
    +0.10
    0.4%
    689
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.17
    0.10
    507
    +0.10
    0.10
    223
    +0.09
    0.10
    Negative Logits
     Proposition
    -0.75
     ÂŃ
    -0.69
     Eighth
    -0.68
    eering
    -0.67
     Gutenberg
    -0.66
     Correctional
    -0.66
     Unified
    -0.65
     Seventh
    -0.64
     Prohibition
    -0.64
     Interstate
    -0.61
    POSITIVE LOGITS
    +.
    1.25
    k
    1.20
    $.
    1.20
    mins
    1.19
    yrs
    1.17
    +)
    1.16
    $,
    1.15
    hr
    1.10
    +
    1.10
    +,
    1.05
    Activations Density 0.651%

    No Known Activations