© 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. 1-RES-JB
    11. 12996
    Prev
    Next
    INDEX
    Explanations

    the word "eventually" in text sequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "eventually."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atures
    -0.84
     Ey
    -0.75
    yre
    -0.73
    hot
    -0.70
    yet
    -0.68
     Sick
    -0.68
    holding
    -0.67
     Gore
    -0.67
    lua
    -0.66
    gent
    -0.66
    POSITIVE LOGITS
     eventually
    1.12
     culmin
    0.99
     destro
    0.94
     migrate
    0.86
     someday
    0.86
    interstitial
    0.84
     culminated
    0.83
     culminating
    0.82
     succumb
    0.82
     reunited
    0.81
    Activations Density 0.015%

    No Known Activations