© 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. 31933
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "w"

    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
    99
    +0.13
    0.6%
    314
    +0.10
    0.4%
    579
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.13
    0.03
    659
    +0.10
    0.03
    18
    +0.10
    0.03
    Negative Logits
     Manifest
    -0.65
    liest
    -0.60
     notch
    -0.60
    ament
    -0.54
     OMG
    -0.54
    Origin
    -0.53
     culp
    -0.53
     Bore
    -0.53
     indu
    -0.53
     Annotations
    -0.52
    POSITIVE LOGITS
    arding
    1.02
    arden
    0.99
    renches
    0.89
    ailable
    0.89
    icket
    0.86
    yk
    0.86
    ithering
    0.85
    erning
    0.85
    arded
    0.84
    sg
    0.84
    Activations Density 0.062%

    No Known Activations