© 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. 8-RES-JB
    11. 6793
    Prev
    Next
    INDEX
    Explanations

    financial values and measurements, such as currency symbols and nutrient quantities

    oai_token-act-pair · gpt-3.5-turbo

    nutritional information or values related to food products

    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
    76561
    -0.78
    poke
    -0.67
    ascript
    -0.67
    ady
    -0.63
    abe
    -0.62
    cele
    -0.61
    è¦ļéĨĴ
    -0.60
    cour
    -0.60
    needed
    -0.60
    itely
    -0.59
    POSITIVE LOGITS
     TOTAL
    0.84
     Conclusion
    0.83
     Flavoring
    0.75
    etc
    0.70
    "},"
    0.67
     Lastly
    0.66
     Torrent
    0.65
     Trends
    0.65
     Mobile
    0.64
     Vinyl
    0.64
    Activations Density 0.416%

    No Known Activations