© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10338
    Prev
    Next
    INDEX
    Explanations

    patterns or pattern-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of patterns and pattern-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omez
    -0.80
    ascular
    -0.75
    venture
    -0.68
    zona
    -0.68
    rican
    -0.67
    assing
    -0.66
    phies
    -0.66
    ULTS
    -0.66
    =-=-=-=-
    -0.65
    UGE
    -0.64
    POSITIVE LOGITS
    gradient
    0.89
     Pattern
    0.86
     pattern
    0.85
    pattern
    0.85
    Pattern
    0.81
     patterns
    0.80
     repeats
    0.78
     Patterns
    0.77
    ĸļ
    0.75
    icity
    0.75
    Activations Density 0.036%

    No Known Activations