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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 1-RES-JB
    6. 8461
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and activities happening on the Senate floor

    oai_token-act-pair · gpt-3.5-turbo

    references to the Senate and legislative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ults
    -0.72
    lag
    -0.71
    eros
    -0.70
     Viking
    -0.67
    venture
    -0.65
    ript
    -0.62
     Vertical
    -0.61
    zsche
    -0.61
    olver
    -0.61
    Property
    -0.60
    POSITIVE LOGITS
     senate
    0.90
     Appropriations
    0.84
    enei
    0.83
    Senate
    0.81
     appropriations
    0.81
    ĸļ
    0.81
     senators
    0.79
    OTUS
    0.78
    sembly
    0.78
     Lyndon
    0.77
    Activations Density 0.592%

    No Known Activations