Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7334
    Prev
    Next
    INDEX
    Explanations

    computer code syntax with specific formatting

    oai_token-act-pair · gpt-3.5-turbo

    non-verbal cues or formatting elements 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
    Not in Any Lists

    No Comments

    Negative Logits
     frontline
    -0.68
     endeavour
    -0.65
     ones
    -0.63
     inexperienced
    -0.63
     unsuccessful
    -0.63
     inexper
    -0.61
     stray
    -0.60
     theatre
    -0.60
     adjud
    -0.59
     resolved
    -0.58
    POSITIVE LOGITS
    Finally
    1.27
    Anyway
    1.21
    Conclusion
    1.16
    Lastly
    1.09
    advertisement
    1.09
    Still
    1.07
    CONCLUS
    1.07
    RAW
    1.06
    Related
    1.00
    Another
    1.00
    Activations Density 0.712%

    No Known Activations