© 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. 1470
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Nelson"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Nelson."

    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
     XY
    -0.83
    cheat
    -0.70
    quest
    -0.69
     decay
    -0.68
    ople
    -0.68
    chat
    -0.68
     ware
    -0.66
     ce
    -0.64
    CHA
    -0.64
    washer
    -0.63
    POSITIVE LOGITS
     Nelson
    3.91
     Mandela
    1.56
    elson
    1.37
     Milton
    1.28
     Benson
    1.24
     Sutton
    1.22
     Robinson
    1.21
     Newman
    1.21
     McKenzie
    1.17
     Cecil
    1.16
    Activations Density 0.020%

    No Known Activations