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. 2-RES-JB
    6. 5116
    Prev
    Next
    INDEX
    Explanations

    references to Driving Under the Influence (DUI) incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to DUI incidents and related statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mahjong
    -0.79
    heimer
    -0.77
     Emin
    -0.76
    ened
    -0.75
    aign
    -0.73
    lé
    -0.71
    lier
    -0.71
     Brah
    -0.67
    bian
    -0.66
    liness
    -0.65
    POSITIVE LOGITS
    ullivan
    0.87
    aird
    0.75
    okin
    0.73
     Dunn
    0.68
    yrim
    0.68
    erva
    0.68
    GBT
    0.68
    atography
    0.67
    nington
    0.67
    uthor
    0.65
    Activations Density 0.029%

    No Known Activations