© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 385
    Prev
    Next
    INDEX
    Explanations

    references to judicial committees in the government

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Judiciary" and related legislative committees

    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
     Viking
    -0.71
    eworld
    -0.68
    orah
    -0.64
    olls
    -0.64
    ettel
    -0.64
    atars
    -0.63
     Valhalla
    -0.62
    ploy
    -0.62
    ages
    -0.61
    ku
    -0.61
    POSITIVE LOGITS
     subcommittee
    1.00
     Judiciary
    0.96
     Committee
    0.88
     Subcommittee
    0.87
     Amendments
    0.86
    iciary
    0.86
     hearings
    0.81
     Caucus
    0.81
    UGH
    0.78
     committee
    0.78
    Activations Density 0.010%

    No Known Activations