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. 3039
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically the name "Deb" at different intensities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Deb" 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
    hyde
    -0.74
    ĸļ
    -0.69
    èĢħ
    -0.67
    XL
    -0.67
     lift
    -0.67
     controller
    -0.67
    Controller
    -0.66
    owl
    -0.66
    ocent
    -0.66
     injection
    -0.65
    POSITIVE LOGITS
     Deb
    3.97
    Deb
    3.21
    deb
    3.08
     deb
    1.94
     Debbie
    1.73
     Debor
    1.53
     Deborah
    1.53
     Debate
    1.31
     Debt
    1.30
     Reb
    1.21
    Activations Density 0.020%

    No Known Activations