© 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. 1-RES-JB
    11. 24182
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals named Sherman and discussions related to antitrust issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.79
    hire
    -0.73
    hest
    -0.69
    err
    -0.68
    here
    -0.67
    versions
    -0.67
    hift
    -0.65
     Libyan
    -0.65
    tk
    -0.65
    ebook
    -0.65
    POSITIVE LOGITS
     Sherman
    1.19
     Oaks
    0.91
     mosqu
    0.86
    agements
    0.85
    ãĤ¼ãĤ¦ãĤ¹
    0.77
    stein
    0.76
    ãĥī
    0.74
    è»
    0.72
    士
    0.72
     Firefly
    0.70
    Activations Density 0.009%

    No Known Activations