© 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. 1-RES-JB
    11. 23219
    Prev
    Next
    INDEX
    Explanations

    keywords related to editing or modifications in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Edit" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phal
    -0.66
    comed
    -0.66
    achy
    -0.64
    ciating
    -0.63
    upp
    -0.63
    eping
    -0.62
    band
    -0.61
    owship
    -0.60
    dimension
    -0.60
    oof
    -0.60
    POSITIVE LOGITS
    Edit
    1.26
    edit
    1.14
     edit
    0.83
     Edit
    0.83
     EDIT
    0.82
    ipedia
    0.82
     Editing
    0.81
     editing
    0.80
    orship
    0.79
    EDIT
    0.77
    Activations Density 0.003%

    No Known Activations