© 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. 4-RES-JB
    11. 8574
    Prev
    Next
    INDEX
    Explanations

    company names, specifically, "Eli Lilly" and "Peyton Manning"

    oai_token-act-pair · gpt-3.5-turbo

    references to the pharmaceutical company Eli Lilly and its related entities

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

    No Comments

    Negative Logits
    luaj
    -0.90
    hips
    -0.85
    xual
    -0.85
    ioned
    -0.80
    feature
    -0.75
    namese
    -0.74
    ĸļ
    -0.73
    tenance
    -0.72
     Debor
    -0.72
    fact
    -0.69
    POSITIVE LOGITS
    ason
    1.02
     Manning
    0.93
     Lilly
    0.92
     Eli
    0.87
    isons
    0.80
     Horowitz
    0.75
    endor
    0.69
     Tot
    0.68
    SON
    0.67
     Schmidt
    0.67
    Activations Density 0.011%

    No Known Activations