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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15543
    Prev
    Next
    INDEX
    Explanations

    terms related to forecasting or predictions

    oai_token-act-pair · gpt-3.5-turbo

    terminology 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 @ 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
    tein
    -0.83
    ansk
    -0.72
    atri
    -0.71
    çĦ
    -0.71
    ĸļ
    -0.70
    adr
    -0.69
    ++++++++++++++++
    -0.69
    atin
    -0.69
    atography
    -0.65
    arantine
    -0.64
    POSITIVE LOGITS
     doom
    0.95
     predictions
    0.88
     predicts
    0.87
     prediction
    0.82
     forecasts
    0.82
     predicting
    0.80
     future
    0.78
    pred
    0.74
    future
    0.74
     forecast
    0.73
    Activations Density 0.067%

    No Known Activations