© 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. 11-RES-JB
    11. 22547
    Prev
    Next
    INDEX
    Explanations

    references to the name "George W. Bush"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "George."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ranked
    -0.72
    eers
    -0.72
    lain
    -0.65
    eer
    -0.64
    nir
    -0.64
    lag
    -0.64
     inhibitor
    -0.63
    unction
    -0.63
     balcon
    -0.62
    Reviewed
    -0.61
    POSITIVE LOGITS
     Soros
    1.15
     Orwell
    1.08
     Clo
    1.01
     Zimmerman
    1.01
     Stephan
    0.91
     HW
    0.90
     RR
    0.90
     Bush
    0.88
     Osborne
    0.88
     Strait
    0.86
    Activations Density 0.027%

    No Known Activations