© 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. 31815
    Prev
    Next
    INDEX
    Explanations

    calls for accountability and justice in societal issues

    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
    246
    +0.11
    0.5%
    86
    +0.11
    0.5%
    53
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.11
    0.13
    665
    +0.11
    0.14
    246
    +0.10
    0.11
    Negative Logits
     Favorite
    -0.75
    onz
    -0.67
     Alc
    -0.65
    ilk
    -0.64
     unlucky
    -0.64
    favorite
    -0.64
     fluct
    -0.61
     Annotations
    -0.61
    enza
    -0.60
    ties
    -0.60
    POSITIVE LOGITS
     rethink
    1.07
     accountable
    1.01
     accountability
    0.98
    arations
    0.94
     reconsider
    0.92
     urgently
    0.91
     acknowledgement
    0.87
    Enough
    0.86
     acknowledgment
    0.86
     repentance
    0.86
    Activations Density 4.083%

    No Known Activations