Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 23359
    Prev
    Next
    INDEX
    Explanations

    the word "wind"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wind energy and wind-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Honor
    -0.65
     attendance
    -0.65
     Lumpur
    -0.61
     Tiff
    -0.61
     Flores
    -0.61
     Lect
    -0.60
     Celebr
    -0.60
     Apprentice
    -0.59
     Constitutional
    -0.59
     Princ
    -0.59
    POSITIVE LOGITS
    mill
    1.32
    blown
    1.26
    shield
    1.22
     turbines
    1.19
    pipe
    1.16
    fall
    1.14
    lass
    1.14
     turbine
    1.13
    lasses
    1.12
    swe
    1.04
    Activations Density 0.038%

    No Known Activations