© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 6769
    Prev
    Next
    INDEX
    Explanations

    keywords related to mechanical components and actions, specifically focusing on bolts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bolt" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olulu
    -0.91
    guyen
    -0.85
    atalie
    -0.77
    vironment
    -0.77
    nesota
    -0.73
    vironments
    -0.70
     fixme
    -0.70
    gregation
    -0.69
    braska
    -0.68
    apolis
    -0.67
    POSITIVE LOGITS
    bolt
    1.33
     bolts
    1.09
     bolt
    1.03
     Bolt
    0.97
    bol
    0.80
    blade
    0.76
    buck
    0.70
     bol
    0.69
     fitt
    0.68
    onite
    0.67
    Activations Density 0.011%

    No Known Activations