© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 7226
    Prev
    Next
    INDEX
    Explanations

    quantitative values such as measurements, percentages, and numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.78
    anim
    -0.77
     sensitive
    -0.72
     morp
    -0.71
     carbohyd
    -0.70
    vertisement
    -0.70
    gre
    -0.70
     plush
    -0.70
     tame
    -0.67
     pse
    -0.67
    POSITIVE LOGITS
     TOTAL
    1.66
     Total
    1.57
     Percentage
    1.43
     Conclusion
    1.38
     Overall
    1.34
     Miscellaneous
    1.31
     Difference
    1.28
     Percent
    1.26
     Average
    1.23
     ----------------------------------------------------------------
    1.20
    Activations Density 0.146%

    No Known Activations