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. 8-RES-JB
    6. 16407
    Prev
    Next
    INDEX
    Explanations

    mentions of political caucuses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "caucus"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.73
     Uz
    -0.71
    Chel
    -0.70
    OTO
    -0.70
    thritis
    -0.70
    uras
    -0.67
    obar
    -0.65
    speed
    -0.65
     warr
    -0.64
    ufact
    -0.63
    POSITIVE LOGITS
    goers
    1.08
     caucuses
    0.94
     caucus
    0.94
    halla
    0.86
     members
    0.86
    atoon
    0.86
     Caucus
    0.83
     member
    0.80
    eers
    0.77
     attendees
    0.76
    Activations Density 0.019%

    No Known Activations