© 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. 18677
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to programming languages and technology

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols that are consistently repeated

    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
    abl
    -0.74
    conn
    -0.71
    zbek
    -0.70
    opian
    -0.69
    });
    -0.67
    lessly
    -0.66
    ously
    -0.65
    .]
    -0.65
    osh
    -0.65
    .''
    -0.65
    POSITIVE LOGITS
     Introduction
    1.11
     Provides
    1.05
     Contains
    1.04
     Completed
    1.03
     Overview
    1.02
     Various
    1.01
     Featuring
    0.99
     Updated
    0.98
     Miscellaneous
    0.97
     Located
    0.97
    Activations Density 0.103%

    No Known Activations