© 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. 20975
    Prev
    Next
    INDEX
    Explanations

    words related to the action of replacing something with another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "replace."

    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
    raq
    -0.82
    vern
    -0.69
    Fight
    -0.66
    haw
    -0.66
     Feeling
    -0.65
    emi
    -0.64
    ucket
    -0.63
    sie
    -0.63
    hoe
    -0.63
    Kind
    -0.62
    POSITIVE LOGITS
    ments
    1.00
    ãĥĺ
    0.89
    mentation
    0.88
     replacement
    0.87
     replacements
    0.86
     obsolete
    0.86
     replace
    0.86
     replaces
    0.86
    mented
    0.82
    orate
    0.79
    Activations Density 0.010%

    No Known Activations