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. 3578
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Rafael"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Rafael" and "Lerner."

    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
    rha
    -0.74
     Asc
    -0.72
    cknowled
    -0.70
    Char
    -0.68
    ibli
    -0.67
    dp
    -0.65
    Cass
    -0.64
     Balk
    -0.63
    orb
    -0.62
     deg
    -0.62
    POSITIVE LOGITS
     Turing
    2.58
     Rafael
    1.82
     Lerner
    1.72
    bt
    1.16
    cade
    1.14
    eport
    1.06
    chery
    0.99
    ICO
    0.99
     Bridgewater
    0.97
     Ernst
    0.96
    Activations Density 0.051%

    No Known Activations