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. 6-RES-JB
    6. 19858
    Prev
    Next
    INDEX
    Explanations

    references to different countries, with a strong emphasis on Russia

    oai_token-act-pair · gpt-3.5-turbo

    references to Russia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.76
    eme
    -0.75
    Score
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.71
    uesday
    -0.70
     Starr
    -0.70
    tc
    -0.68
    Label
    -0.67
    sbm
    -0.66
    pir
    -0.66
    POSITIVE LOGITS
     annexed
    1.00
     Federation
    0.99
    kaya
    0.85
     rou
    0.84
    akov
    0.75
     Dmitry
    0.75
     Today
    0.75
     rall
    0.73
    borg
    0.73
    cius
    0.73
    Activations Density 0.044%

    No Known Activations