© 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. 4-RES-JB
    11. 12259
    Prev
    Next
    INDEX
    Explanations

    phrases related to weather

    oai_token-act-pair · gpt-3.5-turbo

    references to weather

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

    No Comments

    Negative Logits
    onyms
    -0.86
    ony
    -0.76
    rative
    -0.76
    inion
    -0.76
    aepernick
    -0.74
    cca
    -0.72
    zac
    -0.71
    inces
    -0.70
    iasis
    -0.70
    egal
    -0.69
    POSITIVE LOGITS
     Conditions
    0.94
    weather
    0.89
     extremes
    0.85
     forecast
    0.84
     forecasts
    0.80
     fluctuations
    0.79
     Weather
    0.76
     weather
    0.74
     conditions
    0.74
    Weather
    0.74
    Activations Density 0.008%

    No Known Activations