© 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. 7-RES-JB
    11. 7290
    Prev
    Next
    INDEX
    Explanations

    pieces of text containing specific character sequences in a particular order

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÂŃ
    -0.77
     nonexistent
    -0.62
    .""
    -0.61
    ité
    -0.58
    ificate
    -0.57
    —"
    -0.56
     ["
    -0.55
    scl
    -0.55
     âĢ¦"
    -0.55
    existent
    -0.54
    POSITIVE LOGITS
     Conclusion
    0.95
     =================================================================
    0.89
    Conclusion
    0.82
    ¶
    0.80
     =================
    0.77
    CONCLUS
    0.77
    RAW
    0.76
     concludes
    0.75
     Summary
    0.73
    ::::::::
    0.73
    Activations Density 1.357%

    No Known Activations