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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5931
    Prev
    Next
    INDEX
    Explanations

    critical remarks and comments in a text

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to processes or actions associated with organization and efficiency

    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
     oft
    -0.54
     famously
    -0.53
     similarly
    -0.52
     swath
    -0.49
     ("
    -0.48
     twent
    -0.48
     dudes
    -0.48
     scoff
    -0.47
     parity
    -0.47
     lousy
    -0.46
    POSITIVE LOGITS
    urrencies
    0.75
    Allah
    0.64
    Conclusion
    0.60
    oola
    0.59
    urrency
    0.58
    !".
    0.58
     Conclusion
    0.57
     Dhabi
    0.57
    coins
    0.56
    coin
    0.56
    Activations Density 1.529%

    No Known Activations