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. 208
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Jon."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jon."

    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
     carrier
    -0.76
     sectors
    -0.76
     enrol
    -0.75
     unlock
    -0.70
    ocial
    -0.70
     stalls
    -0.70
     unlocks
    -0.70
    EVA
    -0.69
    cel
    -0.69
    ooth
    -0.67
    POSITIVE LOGITS
     Jon
    3.41
    Jon
    2.68
    jon
    1.63
     Jonathan
    1.47
     Jonah
    1.44
     Jaime
    1.37
     Jonas
    1.35
     Ron
    1.34
     Kristen
    1.32
     Thom
    1.29
    Activations Density 0.012%

    No Known Activations