© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 16140
    Prev
    Next
    INDEX
    Explanations

    names, specifically surnames prefixed by 'agg', 'ood', 'orne', 'eth', 'arr', 'agg', 'idd', 'erry', 'unch', 'ald', 'GS' and 'Gerry'

    oai_token-act-pair · gpt-3.5-turbo

    words that express various forms of measurement, classification, or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [*]
    -0.64
     CBI
    -0.61
     mantle
    -0.60
     fundament
    -0.60
     facult
    -0.59
     Vaugh
    -0.59
     AUTHOR
    -0.58
     deed
    -0.57
    Balt
    -0.57
     Gibraltar
    -0.57
    POSITIVE LOGITS
    waukee
    1.05
    gage
    0.92
    nih
    0.92
    intosh
    0.91
    ufact
    0.85
    ogi
    0.82
    gomery
    0.77
    htar
    0.77
    owe
    0.77
    arella
    0.75
    Activations Density 0.371%

    No Known Activations