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. 8-RES-JB
    6. 5531
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Kate" with varying levels of importance or sentiment attached

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kate" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATIONS
    -0.87
    atio
    -0.80
    oresc
    -0.74
    ENSE
    -0.73
    ATIVE
    -0.72
    ensical
    -0.72
    ornia
    -0.70
    indal
    -0.70
    iple
    -0.68
    udic
    -0.68
    POSITIVE LOGITS
     Upton
    1.05
    rina
    0.89
    lyn
    0.86
    vich
    0.84
     Wins
    0.82
    patrick
    0.79
     McCann
    0.79
     Mara
    0.78
    lington
    0.76
    rette
    0.76
    Activations Density 0.021%

    No Known Activations