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. 3962
    Prev
    Next
    INDEX
    Explanations

    proper nouns with the suffix "Sr."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of individuals with the title "Sr" (Senior)

    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
     Beast
    -0.77
     Monsters
    -0.72
     Wonderland
    -0.68
    engu
    -0.66
    book
    -0.66
    ooks
    -0.66
    asty
    -0.65
     Goblin
    -0.64
    Beast
    -0.63
    naire
    -0.62
    POSITIVE LOGITS
     Sr
    3.81
     sr
    1.53
    Äĩ
    1.05
     Sri
    0.92
     paternal
    0.89
    sr
    0.88
     Shank
    0.88
     SR
    0.83
    SR
    0.81
     Croat
    0.80
    Activations Density 0.026%

    No Known Activations