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. 3289
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Timothy"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Timothy" and related derivatives

    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
    Corp
    -0.83
    onga
    -0.75
    abs
    -0.75
     delim
    -0.69
    aut
    -0.69
     pup
    -0.66
    hered
    -0.65
    au
    -0.65
     enum
    -0.64
    ival
    -0.63
    POSITIVE LOGITS
     Timothy
    3.42
     Jeffrey
    1.55
    othy
    1.54
     Kathleen
    1.54
     Christopher
    1.44
     Raymond
    1.42
     Kenneth
    1.40
     Katherine
    1.39
     Geoffrey
    1.35
     Gregory
    1.32
    Activations Density 0.020%

    No Known Activations