© 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 EvalsExportsinterp-engineNEWAPI 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. 12534
    Prev
    Next
    INDEX
    Explanations

    phrases starting with question words and answers or insights related to the question

    oai_token-act-pair · gpt-3.5-turbo

    questions and prompts for further discussion or analysis

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .","
    -0.80
    sed
    -0.70
     âĢķ
    -0.65
    ','
    -0.62
    ""
    -0.62
    .</
    -0.61
    ='
    -0.60
     guiActiveUnfocused
    -0.59
     `
    -0.57
     swe
    -0.57
    POSITIVE LOGITS
     Conclusion
    1.33
     Lastly
    1.11
    Lastly
    1.02
    Conclusion
    0.95
     Finally
    0.94
    Finally
    0.92
     meanwhile
    0.88
    notations
    0.88
     aside
    0.88
    Bottom
    0.87
    Activations Density 0.551%

    No Known Activations