© 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. 17498
    Prev
    Next
    INDEX
    Explanations

    mentions of the university "Emory"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Emory University."

    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
     novelty
    -0.77
     ASC
    -0.69
     Kubrick
    -0.64
     Encyclopedia
    -0.63
     Hawaiian
    -0.63
     Icelandic
    -0.61
    lihood
    -0.61
     Iceland
    -0.61
     wait
    -0.59
     ANGEL
    -0.59
    POSITIVE LOGITS
    otional
    1.51
    otions
    1.49
    phasis
    1.39
    brace
    1.38
    otion
    1.35
    perors
    1.33
    oji
    1.29
    igrant
    1.22
    peror
    1.22
    manuel
    1.15
    Activations Density 0.017%

    No Known Activations