© 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. 0-RES-JB
    11. 18853
    Prev
    Next
    INDEX
    Explanations

    the word "barely"

    oai_token-act-pair · gpt-3.5-turbo

    the word "barely" and its variations, indicating a focus on minimal or insufficient amounts or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Actions
    -0.74
     Individuals
    -0.68
    collection
    -0.68
     Regarding
    -0.66
     Therefore
    -0.65
    ieu
    -0.65
    /
    -0.64
     awa
    -0.63
    farious
    -0.62
     Types
    -0.60
    POSITIVE LOGITS
     barely
    3.11
     scarcely
    1.97
     hardly
    1.90
     rarely
    1.36
     faintly
    1.35
     practically
    1.34
     marginally
    1.33
     vaguely
    1.33
     narrowly
    1.32
     meager
    1.26
    Activations Density 0.013%

    No Known Activations