© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4-RES-JB
    11. 12345
    Prev
    Next
    INDEX
    Explanations

    phrases related to triggering events or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "set off."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    mol
    -0.68
    umbing
    -0.65
    Gall
    -0.61
     laureate
    -0.61
     omn
    -0.60
     entirety
    -0.60
    basketball
    -0.58
     restored
    -0.58
     fix
    -0.57
     intervening
    -0.56
    POSITIVE LOGITS
    cffffcc
    0.84
    ãĥ¤
    0.73
    llor
    0.70
    screen
    0.69
     Tinder
    0.67
    bolt
    0.67
    inar
    0.67
    stage
    0.65
    loading
    0.63
     DEF
    0.62
    Activations Density 0.025%

    No Known Activations