© 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. 9-RES-JB
    11. 23601
    Prev
    Next
    INDEX
    Explanations

    online post features such as "Continue reading," hashtags, and URLs

    oai_token-act-pair · gpt-3.5-turbo

    indicators of content continuation or segmentation in articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.68
     laying
    -0.63
     receivers
    -0.63
    isable
    -0.62
     stewards
    -0.61
    chery
    -0.60
     poles
    -0.59
     sights
    -0.57
     setting
    -0.57
     torped
    -0.57
    POSITIVE LOGITS
     Advertisement
    1.23
    Featured
    1.00
    advertisement
    0.98
     Continued
    0.96
    Correction
    0.92
    VERTISEMENT
    0.91
     GOODMAN
    0.91
     Previous
    0.91
     Comments
    0.89
     SHARES
    0.89
    Activations Density 0.194%

    No Known Activations