© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19282
    Prev
    Next
    INDEX
    Explanations

    the word "won" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "won."

    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
     eff
    -0.67
     «
    -0.67
     main
    -0.65
     versions
    -0.62
     version
    -0.61
     manifest
    -0.61
     temperature
    -0.60
     approximately
    -0.60
     continuous
    -0.60
     process
    -0.60
    POSITIVE LOGITS
    won
    4.54
     Won
    1.83
    earned
    1.27
    wan
    1.15
     won
    1.15
    will
    1.14
    wat
    1.02
    haven
    1.01
    wa
    1.01
    lov
    1.01
    Activations Density 0.011%

    No Known Activations