© 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. 9-RES-JB
    11. 11345
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific concepts and processes involving physical forces and reactions

    oai_token-act-pair · gpt-3.5-turbo

    commas in scientific or academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.76
    leground
    -0.76
    scription
    -0.74
     Wanted
    -0.69
     Memor
    -0.68
    intend
    -0.67
     Equity
    -0.67
     Dynasty
    -0.65
    Books
    -0.65
    ropolitan
    -0.65
    POSITIVE LOGITS
     thereby
    1.14
     causing
    1.10
     suggesting
    1.09
     resulting
    1.08
     indicating
    1.06
     whereas
    1.04
     whereby
    1.01
     which
    0.99
     triggering
    0.98
     implying
    0.93
    Activations Density 0.331%

    No Known Activations