© 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. 1-RES-JB
    11. 24169
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Russia"

    oai_token-act-pair · gpt-3.5-turbo

    references to Russia or discussions about its geopolitical context

    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
    Loc
    -0.80
    eme
    -0.75
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.74
    Template
    -0.72
    abled
    -0.72
    Score
    -0.71
    own
    -0.70
    sbm
    -0.70
    µ
    -0.69
    lder
    -0.69
    POSITIVE LOGITS
    kaya
    0.88
     Ukrain
    0.85
     rall
    0.84
     Russia
    0.82
     Kremlin
    0.80
    iets
    0.78
     rou
    0.77
    Russia
    0.77
     Caucasus
    0.76
     TODAY
    0.76
    Activations Density 0.014%

    No Known Activations