© 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. 6-RES-JB
    11. 997
    Prev
    Next
    INDEX
    Explanations

    government and political terms or entities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utherland
    -0.79
    anyl
    -0.79
     withd
    -0.79
     outlet
    -0.70
    auldron
    -0.66
    itaire
    -0.63
     waterfall
    -0.62
    terday
    -0.62
    oscope
    -0.62
     drill
    -0.61
    POSITIVE LOGITS
    assetsadobe
    0.77
     Conclusion
    0.76
     [+
    0.76
     Mutant
    0.69
     COUR
    0.69
     Mk
    0.69
    AUT
    0.67
    wikipedia
    0.66
     Yon
    0.66
     Coy
    0.64
    Activations Density 0.098%

    No Known Activations