© 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. 11283
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and government bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities, figures, and related terminology

    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
     Brow
    -0.49
     seismic
    -0.48
    imensional
    -0.48
     Era
    -0.48
    Merit
    -0.48
     vortex
    -0.47
     Place
    -0.47
     Amen
    -0.47
    oven
    -0.47
     Filipino
    -0.47
    POSITIVE LOGITS
    tracks
    0.68
    glers
    0.67
    milo
    0.67
    imaru
    0.63
    issance
    0.63
     alike
    0.62
    enance
    0.60
    retty
    0.59
    stice
    0.57
    itiz
    0.57
    Activations Density 0.881%

    No Known Activations