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. 9117
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Lew" followed by different words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lew" in various contexts

    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
    CN
    -0.71
    seat
    -0.69
     ambient
    -0.67
    Container
    -0.64
    pipe
    -0.64
    iPhone
    -0.63
     coupon
    -0.62
     AIR
    -0.62
     Raptors
    -0.62
     subtitles
    -0.61
    POSITIVE LOGITS
     Lew
    4.13
    Lew
    3.70
     Kemp
    1.19
     Gow
    1.18
    Chel
    1.08
     Fey
    1.04
     Levy
    1.00
     Chel
    1.00
     Iw
    0.99
     Morg
    0.98
    Activations Density 0.016%

    No Known Activations