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. 3-RES-JB
    6. 8625
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Wyn" with varying levels of importance

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or entities, particularly those related to names that resemble "Wyn" or "Warn."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unin
    -0.91
     careless
    -0.67
    onom
    -0.66
    gerald
    -0.64
     locality
    -0.64
     predicting
    -0.63
    avez
    -0.63
    doors
    -0.62
    rero
    -0.62
    omsky
    -0.61
    POSITIVE LOGITS
    wyn
    1.38
    robe
    0.90
    er
    0.86
    burn
    0.86
    ת
    0.82
    igans
    0.81
    restling
    0.80
    bridge
    0.79
    yk
    0.79
    asser
    0.75
    Activations Density 0.009%

    No Known Activations