© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 18500
    Prev
    Next
    INDEX
    Explanations

    information about individuals and their accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    statements asserting identity or roles of individuals, particularly in relation to their achievements and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.83
    itized
    -0.74
    escal
    -0.71
    atche
    -0.67
    fail
    -0.67
    >[
    -0.65
    ¢
    -0.65
    stop
    -0.63
     defeats
    -0.63
    uld
    -0.62
    POSITIVE LOGITS
     fluent
    1.13
     currently
    1.13
     credited
    1.10
     renowned
    1.09
     renown
    1.05
     proud
    0.99
     also
    0.98
     passionate
    0.97
     famed
    0.97
     presently
    0.95
    Activations Density 0.193%

    No Known Activations