© 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. 12320
    Prev
    Next
    INDEX
    Explanations

    promotional text with special offers and deals

    oai_token-act-pair · gpt-3.5-turbo

    the presence of bullet points or lists in the text

    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
    •contextual features
    fires on buffer text like "* * *" or "[][][]" or "+ + +"

    No Comments

    Negative Logits
     bast
    -0.72
    bda
    -0.68
     mans
    -0.67
     brute
    -0.62
    wagen
    -0.62
     cle
    -0.61
     sever
    -0.60
    hift
    -0.60
    mans
    -0.59
     subst
    -0.58
    POSITIVE LOGITS
     CONTIN
    0.79
     Chapters
    0.79
     PAGE
    0.75
    --------------------
    0.73
     Conclusion
    0.73
    CHAPTER
    0.73
    ................................................................
    0.73
    ________________________________
    0.73
     <!--
    0.72
    ***
    0.71
    Activations Density 0.078%

    No Known Activations