© 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. 8-RES-JB
    11. 20405
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Scott"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Scott

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ality
    -0.78
    ĺħ
    -0.74
    SHIP
    -0.74
    iotics
    -0.70
    ĵĺ
    -0.70
    iotic
    -0.69
    pread
    -0.66
    senal
    -0.66
    chid
    -0.66
    theless
    -0.63
    POSITIVE LOGITS
     Pruitt
    1.03
     Pilgrim
    1.03
    rade
    0.99
     Walker
    0.97
     Morrison
    0.96
     Olson
    0.92
    inson
    0.91
    inelli
    0.90
    sburg
    0.86
     Horton
    0.86
    Activations Density 0.029%

    No Known Activations