© 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. 4-RES-JB
    11. 667
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or entity named "Thayer" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named "Thayer."

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

    No Comments

    Negative Logits
    bies
    -0.80
    è¯
    -0.71
    egu
    -0.71
     swollen
    -0.68
     swelling
    -0.63
    encers
    -0.62
    obs
    -0.61
    perature
    -0.60
     swell
    -0.59
    pered
    -0.58
    POSITIVE LOGITS
    ayer
    1.04
    ayers
    0.83
    hof
    0.77
    backer
    0.76
    deen
    0.75
    agen
    0.75
    aid
    0.74
    andestine
    0.74
    arette
    0.73
    iquid
    0.72
    Activations Density 0.026%

    No Known Activations