© 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. 0-RES-JB
    11. 8312
    Prev
    Next
    INDEX
    Explanations

    mentions of weather conditions or related words

    oai_token-act-pair · gpt-3.5-turbo

    references to weather-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skim
    -0.73
    clus
    -0.72
     buck
    -0.66
     ko
    -0.66
    cent
    -0.64
    ovo
    -0.63
     cis
    -0.61
     capsules
    -0.60
     binge
    -0.60
     pal
    -0.60
    POSITIVE LOGITS
     Weather
    4.09
    Weather
    3.02
    weather
    2.27
     weather
    2.03
     Climate
    1.28
    Climate
    1.27
     Meteor
    1.26
     Clim
    1.25
     Temper
    1.19
     Winds
    1.16
    Activations Density 0.010%

    No Known Activations