© 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. 3-RES-JB
    11. 15132
    Prev
    Next
    INDEX
    Explanations

    references to forecasting or predictions

    oai_token-act-pair · gpt-3.5-turbo

    references to predictions or projections about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.81
    atin
    -0.73
    cester
    -0.72
    pite
    -0.72
    enes
    -0.71
    ivas
    -0.70
    andro
    -0.69
    VID
    -0.69
    iltration
    -0.68
    Games
    -0.67
    POSITIVE LOGITS
     forecast
    1.27
     forecasts
    1.10
    eering
    0.96
    eers
    0.95
     forecasting
    0.90
     horizon
    0.90
    eer
    0.88
     predicts
    0.87
     predicted
    0.86
     predict
    0.83
    Activations Density 0.018%

    No Known Activations