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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 23950
    Prev
    Next
    INDEX
    Explanations

    U.S. state names with mentions of corresponding political positions or titles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of U.S. states, particularly Texas and Utah

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    blers
    -0.66
    Hidden
    -0.65
     unlaw
    -0.62
    matically
    -0.61
    =-=-=-=-=-=-=-=-
    -0.59
     doc
    -0.58
    Els
    -0.58
     Templ
    -0.57
    uers
    -0.55
     Finnish
    -0.55
    POSITIVE LOGITS
     joins
    0.76
     chairman
    0.76
    who
    0.75
     joined
    0.75
    ohydrate
    0.73
     fame
    0.73
     who
    0.72
     Democrat
    0.71
     whom
    0.71
     tweeted
    0.69
    Activations Density 0.121%

    No Known Activations