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. 8-RES-JB
    6. 7506
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Bruce."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Bruce" mentioned in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.88
    phis
    -0.82
    limits
    -0.81
    sweet
    -0.77
    vg
    -0.74
    xual
    -0.73
    fecture
    -0.73
    ugal
    -0.73
    demand
    -0.72
    yrinth
    -0.71
    POSITIVE LOGITS
     Schne
    1.07
     Jenner
    1.02
     Wayne
    0.89
     Banner
    0.88
     Willis
    0.88
     Sterling
    0.81
     Fein
    0.80
     Spring
    0.79
     Almighty
    0.79
     Hogan
    0.78
    Activations Density 0.023%

    No Known Activations