© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 18669
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically focusing on the South China Sea

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical regions, particularly involving China and its maritime disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erity
    -0.71
    uesday
    -0.66
    roph
    -0.66
    statement
    -0.64
    playing
    -0.64
    elson
    -0.64
    é¾įå
    -0.64
    requ
    -0.63
    kefeller
    -0.62
    berman
    -0.62
    POSITIVE LOGITS
     Lumpur
    0.84
     Sea
    0.79
     Treaty
    0.70
     Pacific
    0.68
     seas
    0.68
     enclave
    0.65
     Authority
    0.65
    iever
    0.65
     Sadd
    0.65
     Emirates
    0.64
    Activations Density 0.056%

    No Known Activations