Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5864
    Prev
    Next
    INDEX
    Explanations

    US state names in the context of political events

    oai_token-act-pair · gpt-3.5-turbo

    references to U.S. states and local political contexts

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

    No Comments

    Negative Logits
    VALUE
    -0.82
     decomp
    -0.75
    selage
    -0.74
    igham
    -0.73
    mercial
    -0.72
    TAG
    -0.72
    ordes
    -0.71
    BOOK
    -0.71
    initions
    -0.69
    uilt
    -0.68
    POSITIVE LOGITS
     electorate
    0.97
     Democratic
    0.90
     Republican
    0.85
     caucus
    0.85
     Caucus
    0.85
     Gov
    0.84
     Governor
    0.83
     voters
    0.83
     Democrats
    0.82
     Congressman
    0.81
    Activations Density 0.187%

    No Known Activations