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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 7347
    Prev
    Next
    INDEX
    Explanations

    references to countries and their associations

    oai_token-act-pair · gpt-3.5-turbo

    references to the country of Lithuania and other Baltic states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cartel
    -0.76
     Scorpion
    -0.75
     Barker
    -0.74
    que
    -0.73
     MU
    -0.71
     Haw
    -0.70
     oil
    -0.69
     TC
    -0.68
    antz
    -0.68
    TC
    -0.68
    POSITIVE LOGITS
     Lithuania
    3.60
     Lithuan
    3.29
     Vil
    2.44
     Baltic
    2.29
     Eston
    2.28
     Estonia
    2.25
     Latvia
    2.20
    uania
    1.90
     Belarus
    1.67
     Balt
    1.56
    Activations Density 0.026%

    No Known Activations