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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15282
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations, particularly countries

    oai_token-act-pair · gpt-3.5-turbo

    references to the Netherlands

    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
    STD
    -0.67
    ARI
    -0.64
    agin
    -0.61
    Anth
    -0.60
    asc
    -0.59
     whim
    -0.59
     gh
    -0.58
    fa
    -0.58
     sustained
    -0.58
     recite
    -0.57
    POSITIVE LOGITS
     Netherlands
    3.85
     Dutch
    2.35
    Dutch
    2.31
     Amsterdam
    2.11
     Hague
    1.81
     Holland
    1.81
     Belgium
    1.81
     Philippines
    1.70
     Denmark
    1.64
     Norway
    1.58
    Activations Density 0.012%

    No Known Activations