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

    Neuronpedia

    APICircuit 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. 14428
    Prev
    Next
    INDEX
    Explanations

    mentions of the country Sri Lanka

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Sri Lanka and related geopolitical contexts

    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
    Adams
    -0.71
     burger
    -0.70
    agent
    -0.64
    andom
    -0.63
     Jenner
    -0.63
    ober
    -0.61
    arrow
    -0.61
     Auction
    -0.61
    Miller
    -0.60
     curves
    -0.59
    POSITIVE LOGITS
     Sri
    4.05
     Lanka
    2.09
     Tamil
    2.07
     Myanmar
    1.64
     Chennai
    1.62
     Nepal
    1.49
     Bangladesh
    1.48
     Thailand
    1.47
     Zimbabwe
    1.46
     Papua
    1.44
    Activations Density 0.015%

    No Known Activations