© 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. 7-RES-JB
    11. 24075
    Prev
    Next
    INDEX
    Explanations

    political race-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "race" and its related context in competitive events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uthor
    -0.76
    SOURCE
    -0.69
     Principle
    -0.68
     Caps
    -0.67
    ighed
    -0.66
     Cargo
    -0.66
    ipedia
    -0.65
    ANG
    -0.63
    ushima
    -0.63
     Publication
    -0.62
    POSITIVE LOGITS
    seat
    0.96
    cand
    0.91
    eering
    0.89
     candidates
    0.89
     fray
    0.86
     challenger
    0.85
     vying
    0.83
     pitted
    0.82
    course
    0.80
     challengers
    0.80
    Activations Density 0.048%

    No Known Activations