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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17752
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Wind" with varied intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept or topic of "wind."

    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
    */(
    -0.75
    ceptor
    -0.67
    UNCH
    -0.67
    cius
    -0.66
    ensitive
    -0.66
     organized
    -0.65
    atern
    -0.65
    avage
    -0.63
    arry
    -0.63
    arij
    -0.62
    POSITIVE LOGITS
    Wind
    1.17
     Wind
    1.16
    wind
    1.09
    shield
    0.94
     Winds
    0.93
    robe
    0.88
    Aid
    0.86
     turbines
    0.85
     turbine
    0.83
    mill
    0.79
    Activations Density 0.002%

    No Known Activations