© 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. 3-RES-JB
    11. 7792
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals holding prestigious positions or titles, particularly that of "president."

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in positions of authority or leadership, particularly those with the title of "president."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eros
    -0.76
    Sharp
    -0.72
     hitch
    -0.71
     srf
    -0.68
    opes
    -0.68
    ratom
    -0.66
     smugglers
    -0.66
    asso
    -0.66
    bane
    -0.65
     exting
    -0.64
    POSITIVE LOGITS
    ially
    1.04
     emer
    0.95
    IAL
    0.91
    boards
    0.86
    lisher
    0.78
    iors
    0.73
    itatively
    0.72
    geist
    0.71
    ority
    0.70
    cies
    0.70
    Activations Density 0.050%

    No Known Activations