© 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. 8-RES-JB
    6. 10047
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe frequency

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that indicate frequency, certainty, or timing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regate
    -0.80
    ortmund
    -0.77
    doms
    -0.76
    would
    -0.72
    might
    -0.72
     Awakens
    -0.71
    enaries
    -0.68
    velt
    -0.68
    ipeg
    -0.67
    idences
    -0.66
    POSITIVE LOGITS
     considered
    1.00
     supposed
    0.97
     going
    0.96
     synonymous
    0.95
     underway
    0.89
     regarded
    0.88
     reversible
    0.88
     irrelevant
    0.87
     accessible
    0.87
     compatible
    0.87
    Activations Density 0.345%

    No Known Activations