© 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. 0-RES-JB
    11. 4080
    Prev
    Next
    INDEX
    Explanations

    names and surnames starting with "Gib"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gibson."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cess
    -0.71
     transit
    -0.65
     tier
    -0.65
     prim
    -0.65
    atched
    -0.64
    OO
    -0.63
     Ä
    -0.63
    node
    -0.62
     app
    -0.62
    Node
    -0.62
    POSITIVE LOGITS
     Gibson
    4.11
     Gib
    1.44
     Brooks
    1.32
     Suzuki
    1.22
     Baldwin
    1.17
     Gibbs
    1.16
     Hicks
    1.16
     Irwin
    1.15
     Watson
    1.13
     Foley
    1.13
    Activations Density 0.013%

    No Known Activations