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. 17086
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to a specific ethnicity or region

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Aziz" and its variations

    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
     stead
    -0.69
     unst
    -0.62
     err
    -0.61
     ownership
    -0.59
     Drivers
    -0.59
     revised
    -0.59
     Minute
    -0.58
     handling
    -0.58
     Replay
    -0.58
     storage
    -0.57
    POSITIVE LOGITS
    azi
    4.65
    az
    1.55
    azy
    1.30
    istani
    1.21
    azer
    1.15
    azo
    1.15
    zee
    1.15
    assi
    1.11
    assian
    1.07
    aza
    1.05
    Activations Density 0.015%

    No Known Activations