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. 19052
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals named Davis

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Davis"

    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
    ãĥĥãĥĪ
    -0.78
    ãĥĦ
    -0.78
    ugal
    -0.73
    azine
    -0.71
     Tayyip
    -0.70
    bably
    -0.69
    abwe
    -0.69
    uncture
    -0.68
    awaru
    -0.67
    IZE
    -0.66
    POSITIVE LOGITS
     Davis
    1.21
    Davis
    1.05
    acre
    0.89
     Hanson
    0.82
    essa
    0.77
    pole
    0.75
    ©¶æ¥µ
    0.73
     Staples
    0.72
     TAMADRA
    0.71
    mouth
    0.70
    Activations Density 0.008%

    No Known Activations