© 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. 0-RES-JB
    11. 18062
    Prev
    Next
    INDEX
    Explanations

    people named "Evan"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Evan" and specific references related to names and their contexts

    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
    ardi
    -0.78
     Kru
    -0.77
    RPG
    -0.73
     Attribution
    -0.72
    loads
    -0.71
     prejud
    -0.71
    Cas
    -0.71
     Blues
    -0.70
     cas
    -0.68
    dp
    -0.67
    POSITIVE LOGITS
     Evan
    3.20
     Upton
    1.27
     Feather
    1.26
     Northwestern
    1.23
     Cran
    1.23
     Olson
    1.20
     feather
    1.17
     Iv
    1.15
     Livingston
    1.12
     Emil
    1.11
    Activations Density 0.038%

    No Known Activations