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. 6092
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named Pete

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Pete" 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
    jad
    -0.73
     Leth
    -0.68
    auri
    -0.67
    iru
    -0.67
     Azerbai
    -0.66
     Qur
    -0.65
     capacity
    -0.65
     unres
    -0.65
     Iranian
    -0.64
    ior
    -0.63
    POSITIVE LOGITS
     Pete
    3.48
     Petersburg
    1.30
     Andy
    1.08
    Andy
    1.08
     Randy
    1.07
     Peggy
    1.04
     Seahawks
    1.03
    ete
    1.02
     Peter
    1.01
     Pablo
    1.00
    Activations Density 0.019%

    No Known Activations