© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4678
    Prev
    Next
    INDEX
    Explanations

    names of characters in films and television

    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
    264
    +0.08
    0.4%
    639
    +0.08
    0.4%
    393
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.08
    0.18
    232
    +0.08
    0.19
    284
    +0.08
    0.14
    Negative Logits
     cryptocurrency
    -0.53
     bulletin
    -0.51
     Canaver
    -0.51
     carefully
    -0.50
     gears
    -0.49
     digitally
    -0.49
     Facts
    -0.49
    pedia
    -0.49
     seriously
    -0.49
     VERS
    -0.48
    POSITIVE LOGITS
     etc
    0.76
    else
    0.73
    )).
    0.73
    ).[
    0.71
    ]);
    0.71
    ))))
    0.70
    ));
    0.69
    alle
    0.69
    )."
    0.68
    ]).
    0.66
    Activations Density 1.763%

    No Known Activations