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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 1085
    Prev
    Next
    INDEX
    Explanations

    numeric values with percentage symbols

    oai_token-act-pair · gpt-3.5-turbo

    high numerical values or percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Partition Features Layer 8 GPT2 Small
    " token" vs "Token"

    No Comments

    Negative Logits
     habit
    -0.81
     trump
    -0.79
     covenant
    -0.77
     manifest
    -0.76
     pitched
    -0.76
     arising
    -0.75
     curly
    -0.73
     applicable
    -0.73
     entrenched
    -0.72
     relevant
    -0.72
    POSITIVE LOGITS
    Advertisements
    1.74
    Conclusion
    1.66
    Others
    1.54
    Other
    1.45
    Total
    1.44
    License
    1.40
    Nor
    1.35
    Trivia
    1.34
    Pan
    1.33
    Summary
    1.32
    Activations Density 0.150%

    No Known Activations