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. 1329
    Prev
    Next
    INDEX
    Explanations

    the name "Dustin" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people, particularly those named Dustin

    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
    lying
    -0.76
    pir
    -0.74
    mega
    -0.74
     actionGroup
    -0.71
    agnetic
    -0.69
    chie
    -0.69
    edy
    -0.68
    fetched
    -0.67
    radio
    -0.66
     charism
    -0.66
    POSITIVE LOGITS
     Dustin
    1.32
     Hoffman
    1.13
    ĸļ
    0.93
     Nguyen
    0.87
    sson
    0.82
     Ortiz
    0.80
     Rasm
    0.80
     Burns
    0.77
     Howe
    0.76
    Dust
    0.76
    Activations Density 0.012%

    No Known Activations