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. 3052
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Johnson"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Johnson" in various contexts

    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
     exams
    -0.82
    eval
    -0.76
     aval
    -0.73
    astery
    -0.70
     Nepal
    -0.69
     ts
    -0.69
    VAL
    -0.68
     burnt
    -0.67
     exam
    -0.67
    Spread
    -0.67
    POSITIVE LOGITS
     Johnson
    3.68
    Johnson
    3.28
     Johnston
    1.61
     Kennedy
    1.37
     Jones
    1.35
     Johns
    1.32
     Owens
    1.32
     Hutchinson
    1.32
     Rowe
    1.31
     Lyndon
    1.30
    Activations Density 0.028%

    No Known Activations