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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 2035
    Prev
    Next
    INDEX
    Explanations

    the word "slack" and variations of it, including different contexts such as relaxation and leniency

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "slack."

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

    No Comments

    Negative Logits
     Celeb
    -0.68
    hetical
    -0.66
     Meier
    -0.66
     Gutenberg
    -0.65
     Lori
    -0.64
    Grand
    -0.64
    icist
    -0.63
     Friendly
    -0.62
     Maggie
    -0.61
    EVA
    -0.61
    POSITIVE LOGITS
     slack
    1.16
    eners
    1.04
    yip
    0.92
    uler
    0.90
    ening
    0.89
    luster
    0.88
    belt
    0.82
    bread
    0.81
    ened
    0.80
    lining
    0.80
    Activations Density 0.007%

    No Known Activations