© 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. 8-RES-JB
    11. 7809
    Prev
    Next
    INDEX
    Explanations

    words related to governmental committees

    oai_token-act-pair · gpt-3.5-turbo

    references to various congressional committees

    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
    ãĤ¨ãĥ«
    -0.80
    erno
    -0.75
    imated
    -0.73
     tul
    -0.70
     tsun
    -0.67
    ifiers
    -0.66
     liner
    -0.65
    ettel
    -0.65
     offline
    -0.64
     Kinnikuman
    -0.63
    POSITIVE LOGITS
     Subcommittee
    1.48
     Committee
    1.35
     Appropriations
    1.34
     subcommittee
    1.30
     Caucus
    1.23
    Senate
    1.14
    committee
    1.07
     committee
    1.05
     Oversight
    1.04
     Senate
    1.02
    Activations Density 0.096%

    No Known Activations