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. 7-RES-JB
    6. 804
    Prev
    Next
    INDEX
    Explanations

    references to a specific person's name (Barnes) across various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Barnes."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffic
    -0.84
    escal
    -0.75
    ppy
    -0.67
    Vi
    -0.63
    pper
    -0.63
    ption
    -0.62
    ptive
    -0.62
     guid
    -0.61
    ple
    -0.61
    ptin
    -0.60
    POSITIVE LOGITS
     Yards
    0.82
    haw
    0.81
     Skydragon
    0.78
    nect
    0.75
    uit
    0.75
    manship
    0.74
    hips
    0.74
     Barnes
    0.74
    halla
    0.74
    yard
    0.71
    Activations Density 0.026%

    No Known Activations