© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 5442
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations related to canals

    oai_token-act-pair · gpt-3.5-turbo

    references to canals, particularly the Suez Canal

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Fundamental
    -0.67
     Emerging
    -0.66
    eting
    -0.64
    RAM
    -0.64
    eff
    -0.64
    rising
    -0.63
    MOD
    -0.63
    err
    -0.62
    ³³³³³³³³³³³³³³³³
    -0.62
     Marketable
    -0.62
    POSITIVE LOGITS
     canal
    1.51
     Canal
    1.38
    wright
    0.98
     reefs
    0.90
    akra
    0.87
     Dock
    0.86
    ufact
    0.80
     ditch
    0.76
    agall
    0.75
     docks
    0.75
    Activations Density 0.006%

    No Known Activations