© 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. 26635
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols within the text

    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
    276
    +0.13
    0.6%
    503
    +0.11
    0.5%
    748
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.13
    0.01
    650
    +0.11
    0.02
    148
    +0.11
    0.02
    Negative Logits
    cephal
    -0.80
    zona
    -0.66
     butterflies
    -0.65
     orgasm
    -0.64
    auga
    -0.64
    wives
    -0.64
     Painter
    -0.63
    ammy
    -0.63
     subconscious
    -0.61
     ILCS
    -0.61
    POSITIVE LOGITS
    ļéĨĴ
    1.57
    ternity
    0.94
    atri
    0.91
    é¾įåĸļ士
    0.88
    éļ
    0.85
    Poké
    0.85
    iscopal
    0.82
    lication
    0.81
    ĸ
    0.81
    ãĥĭ
    0.80
    Activations Density 0.090%

    No Known Activations