© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 8589
    Prev
    Next
    INDEX
    Explanations

    references to developers and development-related topics

    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
    167
    +0.18
    0.8%
    302
    +0.11
    0.5%
    521
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.18
    0.01
    417
    +0.11
    0.02
    269
    +0.10
    0.02
    Negative Logits
    wait
    -0.77
    stals
    -0.73
    ioxide
    -0.72
    ibrary
    -0.68
    neum
    -0.68
     Weasley
    -0.67
    lla
    -0.67
    ls
    -0.65
    xon
    -0.64
    aukee
    -0.63
    POSITIVE LOGITS
     Developers
    0.70
    TAG
    0.69
     Skydragon
    0.68
     Developer
    0.68
    pad
    0.68
    lisher
    0.66
     SDK
    0.65
     à¨
    0.65
    YC
    0.64
     preview
    0.62
    Activations Density 0.116%

    No Known Activations