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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22801
    Prev
    Next
    INDEX
    Explanations

    specific date formats often denoted by 'Week of <month> <day>'

    oai_token-act-pair · gpt-3.5-turbo

    instances of dates, routes, or travel information

    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
     enriched
    -0.83
     liber
    -0.78
     hyp
    -0.77
     retard
    -0.75
     gir
    -0.73
     regener
    -0.72
     brid
    -0.72
     acceler
    -0.71
     begg
    -0.71
     revers
    -0.71
    POSITIVE LOGITS
    Advertisements
    1.52
    Conclusion
    1.48
    --------------------------------------------------------
    1.43
    ================================================================
    1.38
    Contribut
    1.32
    Appearances
    1.29
    Additional
    1.29
    Finally
    1.28
    References
    1.28
    Disclaimer
    1.24
    Activations Density 0.168%

    No Known Activations