© 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. 10-RES-JB
    11. 18745
    Prev
    Next
    INDEX
    Explanations

    names of important figures or personalities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who held previous positions or titles

    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
    omen
    -0.75
    achus
    -0.71
    uden
    -0.70
    abouts
    -0.68
    ramid
    -0.67
    opping
    -0.67
    rought
    -0.67
    ophen
    -0.66
    alion
    -0.66
    owitz
    -0.65
    POSITIVE LOGITS
     Yugoslavia
    1.03
     classmate
    1.03
     colleague
    0.99
     classmates
    0.98
     Yugoslav
    0.96
     teammate
    0.95
     employee
    0.94
     presidents
    0.92
     Soviet
    0.91
     president
    0.89
    Activations Density 0.042%

    No Known Activations