© 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. 9-RES-JB
    11. 18566
    Prev
    Next
    INDEX
    Explanations

    references to geographical regions, particularly focusing on countries in the Asia-Pacific area

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Asia and related regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yard
    -0.88
    vous
    -0.87
    nesday
    -0.84
    Ö¼
    -0.83
    theless
    -0.78
    eret
    -0.76
     CTR
    -0.76
    ensional
    -0.74
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.74
    gotten
    -0.72
    POSITIVE LOGITS
     Pacific
    1.10
     Minor
    1.10
    Pacific
    0.89
     Airlines
    0.89
    orea
    0.88
     tigers
    0.87
    asia
    0.84
     tsunami
    0.82
     Rim
    0.80
     Argent
    0.78
    Activations Density 0.051%

    No Known Activations