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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 11544
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for mentions of the character "Mary Jane Watson."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character Watson from the Sherlock Holmes series

    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
    ð
    -0.72
    ERAL
    -0.71
     unpop
    -0.69
     dracon
    -0.69
     α
    -0.68
     ol
    -0.68
    ren
    -0.67
    eral
    -0.67
    Ren
    -0.66
    ------------------------------------------------
    -0.66
    POSITIVE LOGITS
     Watson
    4.20
    atson
    1.81
     Holmes
    1.58
     Hawkins
    1.29
     Granger
    1.27
     Doyle
    1.24
     Mori
    1.23
     Wolver
    1.19
     Finch
    1.18
     IBM
    1.18
    Activations Density 0.019%

    No Known Activations