© 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. 10-RES-JB
    11. 23311
    Prev
    Next
    INDEX
    Explanations

    references to the name "Bradley" with varying degrees of strength

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Bradley" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ors
    -0.89
    icles
    -0.82
    icle
    -0.78
    packages
    -0.77
    ptions
    -0.76
    orse
    -0.72
    ourced
    -0.71
    orship
    -0.71
    facts
    -0.70
    joined
    -0.68
    POSITIVE LOGITS
     Wiggins
    1.11
     Manning
    1.04
     Cooper
    0.93
     Bradley
    0.90
     Pierce
    0.77
     McD
    0.75
    ton
    0.74
     Sachs
    0.74
    oad
    0.73
     Keane
    0.71
    Activations Density 0.034%

    No Known Activations