Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22143
    Prev
    Next
    INDEX
    Explanations

    terms related to political events, specifically the annexation of Crimea

    oai_token-act-pair · gpt-3.5-turbo

    references to the annexation of Crimea and related geopolitical themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tips
    -0.87
    advertisement
    -0.79
    ä
    -0.76
    gling
    -0.75
    cule
    -0.72
    atively
    -0.71
    ativity
    -0.69
     Petraeus
    -0.69
    ISON
    -0.68
    iggs
    -0.68
    POSITIVE LOGITS
     annexation
    1.05
     Lumpur
    0.95
     annexed
    0.94
     peninsula
    0.93
     Tat
    0.91
     Crimea
    0.86
     Peninsula
    0.83
     Strip
    0.81
     Ukrain
    0.76
     Crimean
    0.75
    Activations Density 0.024%

    No Known Activations