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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 8311
    Prev
    Next
    INDEX
    Explanations

    words related to predictions or forecasting

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zanne
    -0.74
    bestos
    -0.69
    iencies
    -0.67
    ste
    -0.67
    tsy
    -0.64
    cca
    -0.64
    bis
    -0.64
    hist
    -0.63
    gencies
    -0.62
    atin
    -0.62
    POSITIVE LOGITS
     predictions
    1.25
     prediction
    1.11
     forecasts
    1.02
     predicts
    0.94
     Prediction
    0.93
     probabilities
    0.85
     predict
    0.82
     forecast
    0.81
     predicted
    0.81
     accur
    0.79
    Activations Density 0.015%

    No Known Activations