© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22431
    Prev
    Next
    INDEX
    Explanations

    character names within parentheses

    oai_token-act-pair · gpt-3.5-turbo

    open parentheses indicating the start of character references in a narrative

    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
     annex
    -0.86
     legisl
    -0.86
     exporting
    -0.85
     summary
    -0.83
     digest
    -0.81
     quo
    -0.81
     export
    -0.81
     permit
    -0.79
     flow
    -0.79
     adjourn
    -0.78
    POSITIVE LOGITS
    played
    1.80
    who
    1.59
    whose
    1.58
    pictured
    1.53
    aka
    1.43
    formerly
    1.42
    vo
    1.42
    pron
    1.40
    Tom
    1.40
    Danny
    1.39
    Activations Density 0.071%

    No Known Activations