© 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. 9937
    Prev
    Next
    INDEX
    Explanations

    information prompts directing the reader to learn more about a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the desire or invitation to learn additional information

    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
    xtap
    -0.87
    ãĥ¼ãĥĨãĤ£
    -0.71
    adr
    -0.70
    ufact
    -0.69
    uckle
    -0.67
    owder
    -0.66
    quad
    -0.62
    venth
    -0.61
    uble
    -0.61
    uca
    -0.60
    POSITIVE LOGITS
     about
    1.07
     info
    1.02
     details
    0.98
     About
    0.97
    About
    0.95
     ABOUT
    0.94
     than
    0.91
     Info
    0.87
     Details
    0.86
     »
    0.86
    Activations Density 0.031%

    No Known Activations