© 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. 24020
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Sometimes" followed by a statement or observation

    oai_token-act-pair · gpt-3.5-turbo

    the word "sometimes" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    mson
    -0.94
    olitan
    -0.94
    zag
    -0.92
    rats
    -0.77
    isites
    -0.75
    yet
    -0.74
    ongyang
    -0.74
    vich
    -0.73
    elfare
    -0.71
    adra
    -0.69
    POSITIVE LOGITS
    entimes
    0.94
     mistaken
    0.91
     referred
    0.89
     errone
    0.88
    theless
    0.88
     mistakenly
    0.86
    hift
    0.79
     glimps
    0.78
     unconsciously
    0.77
     even
    0.76
    Activations Density 0.034%

    No Known Activations