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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16324
    Prev
    Next
    INDEX
    Explanations

    the word "Walsh" with varying intensities, potentially indicating an association with Walsh in different contexts or opinions

    oai_token-act-pair · gpt-3.5-turbo

    the name "Walsh" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     explanatory
    -0.82
     selective
    -0.82
    ĪĴ
    -0.80
    arial
    -0.80
    iary
    -0.78
    orate
    -0.74
    egal
    -0.74
    arily
    -0.74
    graded
    -0.73
    terior
    -0.72
    POSITIVE LOGITS
     Walsh
    1.13
    enegger
    0.90
    bands
    0.89
     Baldwin
    0.82
     Goodman
    0.78
    restling
    0.78
    quist
    0.78
    hurst
    0.78
    mann
    0.77
     Osw
    0.77
    Activations Density 0.008%

    No Known Activations