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. 1-RES-JB
    6. 23618
    Prev
    Next
    INDEX
    Explanations

    the name "Druce"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named Dru

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eering
    -0.70
    RELATED
    -0.66
     GDDR
    -0.65
     mileage
    -0.65
    ream
    -0.63
    EEE
    -0.61
    éŃĶ
    -0.61
     ripple
    -0.61
    race
    -0.60
    ingly
    -0.60
    POSITIVE LOGITS
     Dru
    1.20
    cler
    0.89
    sonian
    0.82
    oned
    0.79
     dru
    0.77
    bard
    0.77
    ppy
    0.77
    isance
    0.76
    ancer
    0.74
    ancers
    0.72
    Activations Density 0.024%

    No Known Activations