© 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. 9-RES-JB
    11. 10223
    Prev
    Next
    INDEX
    Explanations

    actions related to possession or retention

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "keep."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ode
    -0.80
    NESS
    -0.79
    atana
    -0.74
    ooter
    -0.71
    inals
    -0.68
    iliary
    -0.67
    assi
    -0.67
    sonian
    -0.66
    uably
    -0.65
    KY
    -0.63
    POSITIVE LOGITS
     tabs
    1.27
     track
    1.09
     secrets
    1.02
     afloat
    0.98
     pace
    0.97
     vigil
    0.96
     quiet
    0.95
     secret
    0.92
     kosher
    0.87
     meticulous
    0.84
    Activations Density 0.050%

    No Known Activations