© 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. 1-RES-JB
    11. 20320
    Prev
    Next
    INDEX
    Explanations

    keywords related to wind power and energy

    oai_token-act-pair · gpt-3.5-turbo

    references to wind energy and wind power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unky
    -0.71
    atern
    -0.69
    tein
    -0.66
    akov
    -0.64
    issy
    -0.64
    initions
    -0.62
    arry
    -0.62
    ppard
    -0.61
    earch
    -0.61
    idency
    -0.61
    POSITIVE LOGITS
    Wind
    1.04
    wind
    1.02
     turbines
    0.97
     wind
    0.95
     turbine
    0.95
     Winds
    0.86
    mill
    0.84
    beat
    0.83
    blown
    0.82
    storms
    0.79
    Activations Density 0.009%

    No Known Activations