© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11649
    Prev
    Next
    INDEX
    Explanations

    locations or terms related to the word "keye"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific places and entities, particularly names that include "key" or "eye."

    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
     Flores
    -0.67
     Tau
    -0.67
     Mol
    -0.64
     Poker
    -0.63
     Tribunal
    -0.60
    balance
    -0.60
     utility
    -0.60
     Auction
    -0.59
     blacklist
    -0.59
     Dru
    -0.59
    POSITIVE LOGITS
    keyes
    3.56
    keye
    3.22
     Wolver
    1.34
    eye
    1.32
     Libre
    1.08
    heddar
    1.01
     Fedora
    0.95
    Jennifer
    0.95
     Enix
    0.91
    aneers
    0.90
    Activations Density 0.022%

    No Known Activations