© 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. 20256
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Arnold Schwarzenegger."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Arnold" or "Arnold Schwarzenegger"

    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
    FP
    -0.74
    pace
    -0.70
    PM
    -0.65
     capped
    -0.64
     sealed
    -0.63
     curse
    -0.63
     clutch
    -0.63
    kh
    -0.63
     dash
    -0.63
     gem
    -0.63
    POSITIVE LOGITS
     Arnold
    3.83
     Schwarzenegger
    1.90
    enegger
    1.73
     Irwin
    1.28
     Bauer
    1.13
     Archer
    1.08
     Atkins
    1.08
     Huntington
    1.08
     Norton
    1.07
     Ernst
    1.06
    Activations Density 0.016%

    No Known Activations