© 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. 10-RES-JB
    11. 11262
    Prev
    Next
    INDEX
    Explanations

    phrases indicating troublesome situations or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    statements or comments that conclude with punctuation

    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
    è¦ļéĨĴ
    -0.78
     disembark
    -0.76
     prepar
    -0.74
     haul
    -0.72
     earthqu
    -0.72
    arbon
    -0.72
    urther
    -0.71
     pione
    -0.71
     emanc
    -0.70
    yond
    -0.70
    POSITIVE LOGITS
     Sometimes
    1.48
     Hence
    1.32
     Therefore
    1.32
     Often
    1.31
     Luckily
    1.31
     That
    1.27
     Thus
    1.25
     Usually
    1.25
     Thankfully
    1.22
     Fortunately
    1.22
    Activations Density 0.487%

    No Known Activations