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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7322
    Prev
    Next
    INDEX
    Explanations

    descriptions related to weather conditions

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to weather conditions and temperature extremes

    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
    ingen
    -0.82
     dupl
    -0.74
    borg
    -0.69
     Cyborg
    -0.69
    adr
    -0.68
     Tokens
    -0.66
     disqualified
    -0.66
    Choice
    -0.66
    andowski
    -0.65
     Fame
    -0.65
    POSITIVE LOGITS
     rains
    1.77
     rainy
    1.74
     weather
    1.70
     winter
    1.66
     winters
    1.63
     drought
    1.63
     rain
    1.52
     temperatures
    1.50
     storms
    1.49
     colder
    1.46
    Activations Density 1.308%

    No Known Activations