© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18047
    Prev
    Next
    INDEX
    Explanations

    phrases related to political caucuses

    oai_token-act-pair · gpt-3.5-turbo

    references to political caucuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sour
    -0.72
     karma
    -0.72
     jud
    -0.68
     converting
    -0.65
     tricks
    -0.65
    ear
    -0.64
     property
    -0.63
     speed
    -0.62
     slowing
    -0.62
     bud
    -0.62
    POSITIVE LOGITS
     Caucus
    3.87
    aucus
    1.15
     Railroad
    1.13
     Appropriations
    0.95
     Lobby
    0.95
     Coalition
    0.94
     Cosponsors
    0.94
     Subcommittee
    0.93
     Meadows
    0.91
    ACP
    0.88
    Activations Density 0.017%

    No Known Activations