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. 8563
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dylan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly related to individuals and brands

    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
     Bath
    -0.82
    cheat
    -0.75
    helm
    -0.75
     Spit
    -0.72
     spa
    -0.72
     masc
    -0.71
     Buckingham
    -0.70
     Spa
    -0.69
     Mary
    -0.69
    Sav
    -0.69
    POSITIVE LOGITS
     Dylan
    1.94
     Timbers
    1.73
    ylan
    1.69
     Toyota
    1.62
     Sounders
    1.46
     Clint
    1.31
     Dempsey
    1.30
     Tacoma
    1.26
    yden
    1.16
     Lars
    1.12
    Activations Density 0.043%

    No Known Activations