© 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. 10116
    Prev
    Next
    INDEX
    Explanations

    names of people and organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and organizations

    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
    20439
    -0.65
    chel
    -0.61
     ..."
    -0.53
    berra
    -0.53
    Redd
    -0.50
    /_
    -0.49
    >>>>
    -0.49
    strument
    -0.49
    uff
    -0.49
    chest
    -0.48
    POSITIVE LOGITS
    espie
    0.56
     rul
    0.54
     fared
    0.54
     detractors
    0.53
     responded
    0.49
     countered
    0.48
     blinked
    0.48
    govtrack
    0.48
     Facts
    0.47
     experimented
    0.46
    Activations Density 0.934%

    No Known Activations