© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10538
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named "Danny" with increasing levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Danny."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -1.02
    sites
    -0.84
    atcher
    -0.79
     totality
    -0.70
    ËĪ
    -0.67
    orship
    -0.67
    ament
    -0.67
    nir
    -0.67
    itude
    -0.66
    atches
    -0.65
    POSITIVE LOGITS
     DeV
    0.97
     Amend
    0.93
     Glover
    0.88
     Meyer
    0.81
    Hamilton
    0.80
     Elf
    0.78
     Boyle
    0.76
     Sullivan
    0.70
     Chau
    0.70
     Barron
    0.69
    Activations Density 0.023%

    No Known Activations