© 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. 11291
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental or political issues

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods, and the context surrounding them

    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
    roying
    -0.70
    ãĥĺ
    -0.68
     regener
    -0.66
    urgy
    -0.66
    ļéĨĴ
    -0.65
    essential
    -0.63
    gment
    -0.63
     guts
    -0.62
    agus
    -0.61
    entin
    -0.60
    POSITIVE LOGITS
    Others
    1.07
     Others
    1.04
     Recently
    0.99
     Recent
    0.99
     However
    0.95
    Recently
    0.94
     Critics
    0.91
    Critics
    0.90
    However
    0.89
     commentators
    0.87
    Activations Density 0.692%

    No Known Activations