Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 18452
    Prev
    Next
    INDEX
    Explanations

    phrases related to budget forecasting and economic projections

    oai_token-act-pair · gpt-3.5-turbo

    references to research predictions and economic forecasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.86
    iquette
    -0.85
    Interstitial
    -0.84
    guyen
    -0.78
     Flavoring
    -0.76
     etiquette
    -0.74
     Volunteer
    -0.73
     Chinatown
    -0.71
     actionGroup
    -0.71
     Fem
    -0.70
    POSITIVE LOGITS
     forecasts
    2.15
     forecasting
    2.09
     forecast
    2.00
     predicting
    1.94
     predictions
    1.84
     projections
    1.79
     prediction
    1.75
     predicts
    1.64
     estimating
    1.64
     predicted
    1.59
    Activations Density 0.617%

    No Known Activations