© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14403
    Prev
    Next
    INDEX
    Explanations

    mentions of U.S. Senators

    oai_token-act-pair · gpt-3.5-turbo

    references to senators in a political context

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.75
     Able
    -0.66
     LTD
    -0.66
    senal
    -0.64
    amphetamine
    -0.64
     Kinnikuman
    -0.63
     offline
    -0.62
     Definitive
    -0.62
     Gibraltar
    -0.61
    istically
    -0.60
    POSITIVE LOGITS
    iors
    1.25
    pai
    1.09
     Sen
    1.08
    egal
    1.01
    escent
    0.95
    Sen
    0.93
    esis
    0.89
    uin
    0.87
    ich
    0.84
    gh
    0.84
    Activations Density 0.008%

    No Known Activations