© 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. 11-RES-JB
    11. 22316
    Prev
    Next
    INDEX
    Explanations

    adverbs that emphasize the intensity or degree of change

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that indicate significant changes or impacts

    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
    elsen
    -0.73
    ifully
    -0.69
    aleb
    -0.69
    iem
    -0.69
    aple
    -0.66
    eus
    -0.66
    criptions
    -0.65
    clusively
    -0.64
    afety
    -0.63
    pring
    -0.63
    POSITIVE LOGITS
     outnumbered
    1.10
     reduced
    1.10
     increased
    1.10
     improved
    1.08
     reduce
    1.06
     underestimated
    1.03
     altered
    1.03
     reduces
    1.03
     underest
    1.03
     expanded
    1.02
    Activations Density 0.071%

    No Known Activations