© 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. 11-RES-JB
    11. 17101
    Prev
    Next
    INDEX
    Explanations

    weather-related terms, specifically focusing on precipitation and extreme weather events

    oai_token-act-pair · gpt-3.5-turbo

    weather-related phenomena and extreme weather conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.82
    borg
    -0.81
    utics
    -0.76
    ĸļ
    -0.75
    adr
    -0.74
    uthor
    -0.73
    Token
    -0.73
    mberg
    -0.72
     Neuroscience
    -0.71
     Ethics
    -0.70
    POSITIVE LOGITS
     hail
    1.61
     rains
    1.56
     storms
    1.56
     rain
    1.51
     rainfall
    1.50
     precipitation
    1.49
     landsl
    1.46
     showers
    1.45
     thunder
    1.44
     floods
    1.41
    Activations Density 0.267%

    No Known Activations