© 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. 2-RES-JB
    11. 984
    Prev
    Next
    INDEX
    Explanations

    the term "Patriot" as used in "Patriot Act"

    oai_token-act-pair · gpt-4-turbo

    phrases related to the Patriot Act

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Patriot" relating to the Patriot Act or similar themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redits
    -0.79
    Ļ½
    -0.74
    )=(
    -0.73
    eq
    -0.71
    ð
    -0.71
    forces
    -0.71
    step
    -0.70
    err
    -0.70
    place
    -0.69
    hops
    -0.68
    POSITIVE LOGITS
     Patriot
    1.22
     Prayer
    0.80
     Buster
    0.77
    azines
    0.76
     Yankee
    0.74
     aggregation
    0.72
     Accountability
    0.72
    naire
    0.71
    ica
    0.70
    cia
    0.69
    Activations Density 0.009%

    No Known Activations