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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 6054
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "wing" in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wing."

    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
    ettings
    -0.71
    avez
    -0.66
    NG
    -0.64
     Shinzo
    -0.64
    âĶĢâĶĢ
    -0.62
     Cumber
    -0.62
     Caption
    -0.60
    MRI
    -0.60
    AMA
    -0.60
    fts
    -0.59
    POSITIVE LOGITS
    tips
    1.19
     wing
    1.18
    tip
    1.16
    Wing
    1.06
    nuts
    1.02
     wings
    0.99
    edly
    0.98
    wing
    0.94
    wings
    0.93
    nut
    0.92
    Activations Density 0.006%

    No Known Activations