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. 10-RES-JB
    6. 15275
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "William"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "William."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.87
    pmwiki
    -0.83
    rador
    -0.83
    algia
    -0.74
    raction
    -0.72
    âĸ¬âĸ¬
    -0.67
    ordinate
    -0.66
    ADRA
    -0.66
    âĨij
    -0.65
    effic
    -0.64
    POSITIVE LOGITS
     Hague
    1.03
     Randolph
    1.01
     Shakespeare
    1.00
    son
    0.95
     Jennings
    0.92
    stown
    0.91
     Faul
    0.89
     Weasley
    0.87
     Penn
    0.85
     Byrd
    0.81
    Activations Density 0.032%

    No Known Activations