© 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. 7-RES-JB
    11. 2301
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that imply a critical or evaluative tone

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey criticism or sarcasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ".
    -0.70
    '."
    -0.68
    !".
    -0.63
    ".[
    -0.62
    .''
    -0.59
    ?".
    -0.58
    morrow
    -0.58
    $.
    -0.58
    .""
    -0.57
    ."[
    -0.57
    POSITIVE LOGITS
     quotes
    0.80
     irony
    0.71
     understatement
    0.71
    bole
    0.71
    cerpt
    0.70
     acron
    0.67
     disclaimer
    0.67
    oqu
    0.66
     analogy
    0.66
     excerpt
    0.65
    Activations Density 0.870%

    No Known Activations