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. 24515
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals or places, likely focusing on the name "Buck"

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those of individuals mentioned in a context implying significance or relevance

    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
    amate
    -0.78
     âĸº
    -0.73
     undert
    -0.72
    âĸº
    -0.71
    inburgh
    -0.68
    ãĤ·ãĥ£
    -0.68
    ibur
    -0.67
    bn
    -0.67
     condemn
    -0.66
    quished
    -0.65
    POSITIVE LOGITS
     Buck
    2.12
     Gonzalez
    1.87
     Kris
    1.74
     Sig
    1.48
     Hank
    1.24
     Cris
    1.23
     Cobb
    1.20
     Poe
    1.18
     Dirk
    1.18
     Benn
    1.13
    Activations Density 0.028%

    No Known Activations