© 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. 11-RES-JB
    11. 22624
    Prev
    Next
    INDEX
    Explanations

    the name "Norman" along with other related names or terms like "Osborn," "Nixon," and "Macdonald."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Norman" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Constructed
    -0.91
    Reviewer
    -0.78
    nesses
    -0.72
    externalActionCode
    -0.72
    iasm
    -0.72
    ilee
    -0.70
    ãĤ¿
    -0.69
    qua
    -0.68
    ificial
    -0.68
    iment
    -0.67
    POSITIVE LOGITS
     Eisen
    0.83
    bourg
    0.82
     Schwarz
    0.79
    wald
    0.78
     Bates
    0.74
    wich
    0.74
    beck
    0.73
    gren
    0.72
    ell
    0.72
     Transcript
    0.71
    Activations Density 0.077%

    No Known Activations