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

    Neuronpedia

    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. 0-RES-JB
    11. 5265
    Prev
    Next
    INDEX
    Explanations

    the word "bears" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bears and their relevance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ijn
    -0.82
    ECH
    -0.73
    mess
    -0.69
     String
    -0.64
    itial
    -0.61
    reshold
    -0.61
     Wilkinson
    -0.60
    istry
    -0.60
    ussen
    -0.59
     Wesley
    -0.59
    POSITIVE LOGITS
     bears
    3.85
     bear
    2.61
     Bear
    1.82
    Bear
    1.78
     Bears
    1.76
    bear
    1.72
     grizz
    1.43
     tigers
    1.43
     bore
    1.40
     lions
    1.29
    Activations Density 0.006%

    No Known Activations