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. 9-RES-JB
    6. 6649
    Prev
    Next
    INDEX
    Explanations

    brief questions or statements with pauses or parenthetical interruptions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and 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 @ 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
    SPONSORED
    -0.86
    CVE
    -0.77
    Advertisement
    -0.75
    --
    -0.67
    î
    -0.66
    .*
    -0.66
    ubs
    -0.66
    ``
    -0.65
    âĢķ
    -0.64
    aster
    -0.64
    POSITIVE LOGITS
     Ibid
    1.23
     Lastly
    1.22
     Various
    1.21
     Finally
    1.17
     Conclusion
    1.12
     Speaking
    1.05
     Numerous
    1.05
     Miscellaneous
    1.04
     Unable
    1.02
     Lots
    1.02
    Activations Density 0.189%

    No Known Activations