© 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. 24044
    Prev
    Next
    INDEX
    Explanations

    the name "Santorum"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Rick Santorum

    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
    ership
    -0.78
    ĪĴ
    -0.75
    arding
    -0.71
    urden
    -0.71
    uilding
    -0.71
    edded
    -0.70
    illard
    -0.70
    oard
    -0.70
    ed
    -0.69
    orney
    -0.69
    POSITIVE LOGITS
     Santorum
    0.83
     Slug
    0.77
    craft
    0.75
    Å¡
    0.72
    atsuki
    0.70
    nyder
    0.70
    bands
    0.69
    CHAT
    0.68
    kies
    0.65
    kamp
    0.64
    Activations Density 0.010%

    No Known Activations