© 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. 1208
    Prev
    Next
    INDEX
    Explanations

    references to communication through email and casual conversation

    oai_token-act-pair · gpt-3.5-turbo

    indicators of communication and social interactions

    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
     awaits
    -0.84
     await
    -0.70
    UGC
    -0.65
    currently
    -0.64
    must
    -0.62
    anse
    -0.62
     SHALL
    -0.62
     Alternatively
    -0.61
     remains
    -0.61
     comprises
    -0.61
    POSITIVE LOGITS
    ,'"
    1.15
    .""
    1.15
     ['
    1.12
    ,"
    1.12
    ."
    1.09
     [
    1.09
     yesterday
    1.07
    .")
    1.06
    .,"
    1.06
    ."[
    1.06
    Activations Density 0.570%

    No Known Activations