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. 9-RES-JB
    6. 8549
    Prev
    Next
    INDEX
    Explanations

    mentions of weather-related agencies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to meteorological agencies and weather conditions in Japan

    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
    uliffe
    -0.90
     BLM
    -0.88
     Alexandria
    -0.84
     Webb
    -0.82
     loaf
    -0.80
     Gibbs
    -0.80
    Virginia
    -0.79
    espie
    -0.79
     Dixon
    -0.79
     Malone
    -0.78
    POSITIVE LOGITS
     Japan
    1.89
    Japanese
    1.83
     Japanese
    1.83
     Tokyo
    1.78
    Japan
    1.78
    Tok
    1.73
     Osaka
    1.73
     Fuji
    1.65
     Hiro
    1.56
     Yosh
    1.54
    Activations Density 0.404%

    No Known Activations