© 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. 2383
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wind," likely indicating a focus on winds and windy conditions or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to "wind" in various contexts

    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
    Ô
    -0.62
     expended
    -0.61
    ĸļ
    -0.60
     Bacon
    -0.59
    UNCH
    -0.59
     charge
    -0.58
     subsistence
    -0.58
     interchangeable
    -0.57
    ©¶æ
    -0.57
    ĺħ
    -0.57
    POSITIVE LOGITS
    wind
    1.39
    shield
    0.95
    beat
    0.91
     Solitaire
    0.90
    Wind
    0.89
    robe
    0.88
    mill
    0.85
    WIND
    0.82
    trap
    0.81
     wip
    0.81
    Activations Density 0.009%

    No Known Activations