© 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
    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. 13363
    Prev
    Next
    INDEX
    Explanations

    words related to political bills or legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to specific legislative bills

    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
    OVA
    -0.67
    liction
    -0.65
    vent
    -0.65
     Pv
    -0.64
    ystem
    -0.62
    inction
    -0.62
     Sul
    -0.62
    ertain
    -0.62
     Ashes
    -0.62
     Drift
    -0.60
    POSITIVE LOGITS
    iard
    1.37
     bill
    1.08
    bill
    0.97
     bills
    0.95
    BILL
    0.86
    boards
    0.79
    owing
    0.78
    interstitial
    0.77
    book
    0.77
    ows
    0.75
    Activations Density 0.026%

    No Known Activations