© 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. 9-RES-JB
    11. 15535
    Prev
    Next
    INDEX
    Explanations

    names of politicians and their respective states

    oai_token-act-pair · gpt-3.5-turbo

    references to U.S. senators and their associated states or political affiliations

    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
     pim
    -0.75
    llah
    -0.74
    DragonMagazine
    -0.71
     glim
    -0.69
     Wenger
    -0.68
     emanc
    -0.68
    cms
    -0.68
     runway
    -0.66
    Reviewer
    -0.66
     IDF
    -0.65
    POSITIVE LOGITS
     Kentucky
    1.06
     Florida
    1.00
     Ohio
    1.00
     Idaho
    0.98
     Minnesota
    0.98
     Tennessee
    0.97
     Arizona
    0.97
     Utah
    0.96
     Pennsylvania
    0.95
     Texas
    0.95
    Activations Density 0.081%

    No Known Activations