© 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. 18724
    Prev
    Next
    INDEX
    Explanations

    names of people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people and organizations

    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
    !),
    -0.84
    !",
    -0.83
    !).
    -0.79
    !'"
    -0.74
    !".
    -0.72
    .ãĢį
    -0.71
     anymore
    -0.71
    !:
    -0.68
     toget
    -0.67
     psychiat
    -0.67
    POSITIVE LOGITS
     TP
    0.95
     RTX
    0.90
     IMAGES
    0.87
    <|endoftext|>
    0.84
     REUTERS
    0.80
     UNITED
    0.79
     Buy
    0.78
     Protesters
    0.77
     Dug
    0.75
     Generic
    0.74
    Activations Density 0.045%

    No Known Activations