© 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 EvalsExportsAPI 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. 28301
    Prev
    Next
    INDEX
    Explanations

    file types and various media formats

    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
    373
    +0.17
    0.8%
    521
    +0.11
    0.5%
    461
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.17
    0.00
    487
    +0.11
    0.01
    165
    +0.10
    0.00
    Negative Logits
    zsche
    -0.80
    lict
    -0.77
     spons
    -0.76
    dos
    -0.75
     offending
    -0.74
    bage
    -0.73
    onis
    -0.73
     tamp
    -0.71
    coded
    -0.70
    ministic
    -0.69
    POSITIVE LOGITS
    6666
    0.97
    66666666
    0.73
     Rothschild
    0.72
    ãĥ³ãĤ¸
    0.71
     Almighty
    0.70
     Goodman
    0.69
     Royals
    0.69
     --------------------------------
    0.69
     Monroe
    0.68
     Video
    0.67
    Activations Density 0.078%

    No Known Activations