© 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 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. 9-RES-JB
    11. 1920
    Prev
    Next
    INDEX
    Explanations

    names of politicians or political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to political voting and actions of politicians

    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
    Ö
    -0.66
    washer
    -0.63
     Hust
    -0.63
    cest
    -0.62
    anny
    -0.62
     Prev
    -0.62
    ãĤ´
    -0.62
    TYPE
    -0.61
    ById
    -0.61
     lull
    -0.60
    POSITIVE LOGITS
     respective
    0.99
     respectively
    0.92
    osponsors
    0.90
     departures
    0.83
     apiece
    0.81
     collectively
    0.80
     defect
    0.80
     endorsements
    0.80
     participating
    0.79
     signatures
    0.79
    Activations Density 0.580%

    No Known Activations