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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 15259
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Mathieu"

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular individual or entity, likely "Matthew."

    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
    è¦ļéĨĴ
    -0.83
     Cosponsors
    -0.78
    ications
    -0.78
    iary
    -0.77
    20439
    -0.73
    imony
    -0.73
    icating
    -0.72
    ifiable
    -0.71
    ication
    -0.70
    icated
    -0.69
    POSITIVE LOGITS
    vre
    0.95
    lette
    0.85
    llor
    0.82
    llo
    0.80
    vernment
    0.80
    Å¡
    0.80
     versa
    0.77
    raud
    0.76
    ieu
    0.75
    Ëľ
    0.75
    Activations Density 0.010%

    No Known Activations