© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22160
    Prev
    Next
    INDEX
    Explanations

    phrases containing the adjective "plain."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "plain" and its variations, often in the context of simplicity or straightforwardness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otos
    -0.72
    oleon
    -0.66
    essed
    -0.66
    umar
    -0.65
    ulic
    -0.64
     chronically
    -0.64
     Prescott
    -0.64
     Ascend
    -0.63
    orous
    -0.62
    hner
    -0.62
    POSITIVE LOGITS
    text
    1.10
    cl
    1.07
    cloth
    0.94
     ol
    0.90
     Dealer
    0.87
     clothes
    0.87
     sight
    0.87
    rolled
    0.86
     english
    0.85
     vanilla
    0.84
    Activations Density 0.032%

    No Known Activations