© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 20481
    Prev
    Next
    INDEX
    Explanations

    references to U.S. Senators by their title

    oai_token-act-pair · gpt-3.5-turbo

    references to U.S. Senators

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ATHER
    -0.66
    istically
    -0.65
     Gauntlet
    -0.64
     casing
    -0.63
     Firefly
    -0.63
     Pax
    -0.61
     LTD
    -0.61
     HMS
    -0.61
     Brist
    -0.60
     Cologne
    -0.60
    POSITIVE LOGITS
    iors
    1.30
    egal
    1.19
    pai
    1.13
    Sen
    1.09
    escent
    1.04
    eca
    0.92
    ileaks
    0.88
    uary
    0.86
    ior
    0.85
    ky
    0.83
    Activations Density 0.004%

    No Known Activations