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. 9040
    Prev
    Next
    INDEX
    Explanations

    keywords related to the specific term "Hyde" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals and brands

    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
     bet
    -0.71
    asus
    -0.67
     sear
    -0.66
     cargo
    -0.65
    gan
    -0.65
     corrections
    -0.64
    cast
    -0.64
     Î
    -0.64
     onboard
    -0.63
    cens
    -0.60
    POSITIVE LOGITS
     Hyde
    4.39
    Hy
    1.36
     Hamp
    1.15
    hyde
    1.13
     Notting
    1.12
     Roose
    1.12
     Marble
    1.10
     Garfield
    1.09
     Brighton
    1.08
     Bedford
    1.08
    Activations Density 0.026%

    No Known Activations