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. 1-RES-JB
    6. 16987
    Prev
    Next
    INDEX
    Explanations

    terms related to the annexation of Crimea

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Crimea and its annexation

    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
    cule
    -0.83
    gling
    -0.78
    ISA
    -0.74
    Hug
    -0.72
    advertisement
    -0.70
    Label
    -0.70
    Murray
    -0.69
    NES
    -0.69
    Advertisements
    -0.68
    fm
    -0.68
    POSITIVE LOGITS
     Crimea
    1.07
     annexation
    1.01
     Ukrain
    0.96
     annexed
    0.89
     Tat
    0.85
     Crimean
    0.82
    thal
    0.82
    icter
    0.78
    EStream
    0.77
     Bots
    0.74
    Activations Density 0.008%

    No Known Activations