© 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. 1-RES-JB
    11. 3363
    Prev
    Next
    INDEX
    Explanations

    phrases related to making predictions or forecasts for various situations or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to predictions and forecasting

    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
    pite
    -0.83
    Interstitial
    -0.81
    aque
    -0.71
     IMAGES
    -0.69
    cester
    -0.68
    ivas
    -0.68
    aughs
    -0.67
    uggage
    -0.67
    culture
    -0.67
    avery
    -0.66
    POSITIVE LOGITS
     forecast
    1.44
     forecasts
    1.29
     forecasting
    1.01
     predictions
    0.97
     prediction
    0.95
     predicted
    0.92
    eering
    0.91
     outlook
    0.91
    eers
    0.88
     predict
    0.87
    Activations Density 0.006%

    No Known Activations