© 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. 4-RES-JB
    11. 22212
    Prev
    Next
    INDEX
    Explanations

    mentions of amphitheaters and other related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to amphitheaters or similar performance venues

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

    No Comments

    Negative Logits
     Benz
    -0.75
     Leilan
    -0.72
    lished
    -0.68
     penetrating
    -0.66
    enegger
    -0.64
     Origin
    -0.64
     Squirrel
    -0.63
     developing
    -0.61
     Annotations
    -0.61
     Prediction
    -0.60
    POSITIVE LOGITS
    ithe
    1.41
    atre
    1.35
    selage
    0.96
    aviour
    0.91
    rette
    0.90
    aque
    0.88
    tesy
    0.88
    aton
    0.87
    reen
    0.86
    gregation
    0.85
    Activations Density 0.009%

    No Known Activations