© 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. 6-RES-JB
    11. 14882
    Prev
    Next
    INDEX
    Explanations

    the word "predict" or variations of it with high activations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to forecasting and predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atin
    -0.79
    tha
    -0.72
    atri
    -0.71
    undy
    -0.70
    unal
    -0.67
    ento
    -0.66
    ansk
    -0.65
    dx
    -0.63
    bestos
    -0.63
    plom
    -0.62
    POSITIVE LOGITS
     doom
    0.85
     forecasts
    0.84
     predictions
    0.83
     predicts
    0.82
     predict
    0.81
     prediction
    0.79
    pred
    0.78
    itability
    0.76
     Prediction
    0.76
     predicting
    0.75
    Activations Density 0.032%

    No Known Activations