© 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. 7846
    Prev
    Next
    INDEX
    Explanations

    names or words containing the sound "sh"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "sh" in various contexts

    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
     caring
    -0.68
     swing
    -0.63
     circulation
    -0.63
     numbered
    -0.62
     Swed
    -0.62
     Luther
    -0.57
     Appropriations
    -0.56
     hopping
    -0.55
     knowing
    -0.54
     Leth
    -0.54
    POSITIVE LOGITS
    ackle
    0.94
    uffle
    0.91
    rimp
    0.89
    nikov
    0.89
    ahn
    0.88
    ospital
    0.88
    akh
    0.87
    uler
    0.85
    auna
    0.85
    REE
    0.85
    Activations Density 0.034%

    No Known Activations