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. 3-RES-JB
    6. 22004
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to media personalities

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals, specifically focusing on the surname Clarkson

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctions
    -0.84
    LOAD
    -0.83
    externalActionCode
    -0.76
    NING
    -0.75
    cgi
    -0.68
    vironment
    -0.66
    fortune
    -0.63
     Ult
    -0.62
     Habit
    -0.61
    Fi
    -0.61
    POSITIVE LOGITS
     Clarkson
    1.33
     Chapman
    0.80
     McH
    0.79
     Hammond
    0.76
    obyl
    0.73
    owell
    0.71
     Dickinson
    0.70
     Paddock
    0.69
     Kem
    0.68
     Barrett
    0.67
    Activations Density 0.011%

    No Known Activations