© 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. 8-RES_POST_32K-OAI
    11. 8633
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'J' followed by a period

    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
    594
    +0.10
    0.5%
    19
    +0.10
    0.4%
    350
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.02
    632
    +0.10
    0.02
    335
    +0.09
    0.02
    Negative Logits
    milo
    -0.78
    holders
    -0.71
    lesh
    -0.69
    ulum
    -0.69
    holder
    -0.67
    iple
    -0.65
    iola
    -0.65
    ueless
    -0.63
    mania
    -0.63
    yrics
    -0.62
    POSITIVE LOGITS
    ournal
    0.82
     Siber
    0.76
     Edgar
    0.71
    yll
    0.68
     Pier
    0.68
     Nutr
    0.67
     Jonah
    0.66
     Hicks
    0.66
     Sawyer
    0.66
    Ax
    0.65
    Activations Density 0.065%

    No Known Activations