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. 0-RES-JB
    6. 10965
    Prev
    Next
    INDEX
    Explanations

    instances of the word "introduce"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "introduce" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tery
    -0.67
     Rage
    -0.67
    oros
    -0.66
     righteous
    -0.65
     rage
    -0.65
     Wa
    -0.64
     Sioux
    -0.64
     Salem
    -0.64
     Washington
    -0.63
     Bureau
    -0.62
    POSITIVE LOGITS
     introduce
    3.65
     introducing
    2.73
     introduces
    2.57
    introdu
    2.49
     introduced
    2.42
     reintrodu
    2.36
     Introdu
    2.07
     introduction
    2.04
     introdu
    2.03
    Introdu
    2.01
    Activations Density 0.021%

    No Known Activations