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. 3509
    Prev
    Next
    INDEX
    Explanations

    terms related to being a pioneer or being pioneering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to innovation and leadership in various fields

    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
    allah
    -0.79
     ORDER
    -0.78
    alia
    -0.73
     Dinner
    -0.68
     Oval
    -0.67
    Things
    -0.66
     Tweet
    -0.66
    Accessory
    -0.66
     Kislyak
    -0.64
    Email
    -0.63
    POSITIVE LOGITS
     pioneer
    2.89
     pioneers
    2.64
     proponent
    1.71
     pioneering
    1.66
     proponents
    1.56
     inventor
    1.33
     innov
    1.32
     theorist
    1.25
     explorers
    1.19
     practitioners
    1.18
    Activations Density 0.034%

    No Known Activations