© 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. 12-RES-JB
    11. 2538
    Prev
    Next
    INDEX
    Explanations

    mentions of actions or events labeled with terms like "call," "calls," "calling," and "called."

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases that involve the act of calling or labeling something

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Debor
    -0.58
     attach
    -0.57
     retrie
    -0.52
    Which
    -0.50
     amd
    -0.49
    iers
    -0.49
     Which
    -0.47
    iard
    -0.47
    ecided
    -0.47
     answ
    -0.47
    POSITIVE LOGITS
    Operation
    0.79
     routine
    0.72
     madness
    0.67
     willful
    0.66
     wasteful
    0.64
     exemplary
    0.64
     unfair
    0.64
     insanity
    0.63
     egregious
    0.63
     intolerable
    0.63
    Activations Density 0.220%

    No Known Activations