© 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. 7-RES-JB
    11. 19078
    Prev
    Next
    INDEX
    Explanations

    phrases related to the fictional character Sherlock Holmes

    oai_token-act-pair · gpt-3.5-turbo

    references to Sherlock Holmes and related characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acid
    -0.89
    lag
    -0.86
    ramid
    -0.79
    issan
    -0.78
    pell
    -0.76
    utonium
    -0.73
    manuel
    -0.73
    assault
    -0.72
    ilater
    -0.72
    rm
    -0.72
    POSITIVE LOGITS
     Holmes
    1.47
     Cumber
    1.14
    batch
    1.08
     Sherlock
    0.88
     Doyle
    0.86
    Lens
    0.76
     Grimes
    0.73
    itial
    0.71
     âĸº
    0.70
     XVI
    0.70
    Activations Density 0.053%

    No Known Activations