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. 1-RES-JB
    6. 19887
    Prev
    Next
    INDEX
    Explanations

    references to sunny weather

    oai_token-act-pair · gpt-3.5-turbo

    mentions of weather conditions, particularly sunny weather

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LESS
    -0.82
    ingo
    -0.81
    ravings
    -0.74
    atern
    -0.73
    library
    -0.72
    eki
    -0.71
    argon
    -0.71
    uf
    -0.71
    ĸļ
    -0.70
    ngth
    -0.68
    POSITIVE LOGITS
     sunny
    1.28
     skies
    0.96
     Sunny
    0.96
     cloudy
    0.92
     luc
    0.78
     paradise
    0.77
     rainy
    0.76
     calm
    0.75
     sunshine
    0.75
     weather
    0.73
    Activations Density 0.008%

    No Known Activations