© 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. 3-RES-JB
    11. 9810
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Belarus" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the country Belarus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARD
    -0.73
    ODUCT
    -0.72
    ded
    -0.70
    flush
    -0.67
    ointed
    -0.67
    hedon
    -0.66
    ocard
    -0.66
    ds
    -0.66
    ptive
    -0.66
    rocal
    -0.65
    POSITIVE LOGITS
    insk
    0.97
    etsk
    0.85
    ian
    0.83
    £ı
    0.79
    ians
    0.78
     Belarus
    0.77
    nuts
    0.73
     Kazakhstan
    0.73
     dab
    0.72
     Bots
    0.72
    Activations Density 0.008%

    No Known Activations