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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 16334
    Prev
    Next
    INDEX
    Explanations

    mentions of Russian names ending in 'kov'

    oai_token-act-pair · gpt-3.5-turbo

    names and references associated with individuals, particularly those of Russian origin or in relation to Russian politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASED
    -0.67
    forest
    -0.67
     NCT
    -0.67
    roads
    -0.67
     Printed
    -0.67
    coat
    -0.65
     WOM
    -0.64
    usted
    -0.62
    Forest
    -0.62
    ãĥĨ
    -0.61
    POSITIVE LOGITS
    sky
    1.37
    ski
    1.34
    achev
    1.12
    atti
    1.04
    hattan
    1.01
    kov
    1.00
    tein
    1.00
    akov
    0.99
    lov
    0.89
    etsk
    0.87
    Activations Density 0.023%

    No Known Activations