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. 8883
    Prev
    Next
    INDEX
    Explanations

    words related to the surname "Hawker"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kershaw."

    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
     pornographic
    -0.71
     subs
    -0.70
     Serbian
    -0.67
     Lucius
    -0.67
     Prague
    -0.66
     Sergei
    -0.63
     stat
    -0.62
     prim
    -0.61
     instant
    -0.61
     millions
    -0.60
    POSITIVE LOGITS
    haw
    5.11
    Haw
    1.73
    hops
    1.29
    hawk
    1.28
    hur
    1.28
    hop
    1.18
     Haw
    1.17
     haw
    1.16
    haul
    1.13
    mith
    1.11
    Activations Density 0.020%

    No Known Activations