© 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. 10-RES-JB
    6. 13612
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis commonly expressed using repeated words

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intensity or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.80
     guiActiveUn
    -0.66
    tnc
    -0.66
    Deploy
    -0.65
    ãĤ´
    -0.64
    î
    -0.64
    %:
    -0.63
     Citiz
    -0.63
    Ô
    -0.62
    Export
    -0.62
    POSITIVE LOGITS
     REALLY
    1.34
     really
    1.29
    really
    1.24
     Really
    1.01
     uh
    0.99
     truly
    0.97
     um
    0.94
     genuinely
    0.88
    yip
    0.86
     honestly
    0.84
    Activations Density 0.051%

    No Known Activations