© 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 EvalsExportsAPI 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. 21764
    Prev
    Next
    INDEX
    Explanations

    countries in Eastern Europe, specifically Slovakia and Slovenia

    oai_token-act-pair · gpt-3.5-turbo

    references to the country Slovakia and related terms

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    rient
    -0.90
    rients
    -0.86
    gdala
    -0.84
    agonist
    -0.81
    gered
    -0.80
    nels
    -0.79
    lisher
    -0.79
    urate
    -0.78
    seller
    -0.78
    corn
    -0.76
    POSITIVE LOGITS
     Slov
    1.34
     Slovakia
    1.34
     Sloven
    1.13
     Slovenia
    1.05
     Czech
    0.91
    oslov
    0.89
    Äį
    0.83
     Buch
    0.82
     Isles
    0.81
     Belarus
    0.80
    Activations Density 0.007%

    No Known Activations