© 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. 31234
    Prev
    Next
    INDEX
    Explanations

    statements involving the correctness or validation of opinions or beliefs

    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
    102
    +0.14
    0.7%
    324
    +0.10
    0.5%
    200
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.14
    0.21
    55
    +0.10
    0.17
    566
    +0.10
    0.15
    Negative Logits
    venant
    -0.79
     ILCS
    -0.71
    ulton
    -0.70
    letal
    -0.69
    atcher
    -0.66
    ursed
    -0.66
    clerosis
    -0.66
     Ribbon
    -0.65
    icipated
    -0.65
    atches
    -0.63
    POSITIVE LOGITS
     referring
    1.61
     correct
    1.48
     wrong
    1.42
     kidding
    1.38
     joking
    1.37
     referencing
    1.35
     quoting
    1.34
     implying
    1.31
     incorrect
    1.27
     talking
    1.27
    Activations Density 1.123%

    No Known Activations