© 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. 0-RES-JB
    11. 4205
    Prev
    Next
    INDEX
    Explanations

    the word "projected."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to forecasts or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij
    -0.71
    bug
    -0.68
    law
    -0.66
    sie
    -0.66
    ful
    -0.63
     Bug
    -0.62
    kn
    -0.62
    icia
    -0.62
    hurst
    -0.62
    recy
    -0.61
    POSITIVE LOGITS
     projected
    3.64
     projecting
    2.02
     projections
    1.98
     predicted
    1.89
     projection
    1.87
     forecast
    1.69
     anticipated
    1.68
     estimated
    1.68
     expected
    1.50
     projector
    1.50
    Activations Density 0.013%

    No Known Activations