© 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. 10324
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or directives

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs related to decision-making and achievement

    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
     ][
    -0.62
    ortium
    -0.59
     Ung
    -0.59
     Located
    -0.59
    >>\
    -0.57
     Cinema
    -0.55
    perty
    -0.55
     Gamble
    -0.55
    culus
    -0.54
     <[
    -0.54
    POSITIVE LOGITS
     accordingly
    1.21
     yourself
    0.93
    able
    0.89
     ourselves
    0.89
    ments
    0.89
     alike
    0.88
     yourselves
    0.87
     versa
    0.86
     oneself
    0.85
    ables
    0.84
    Activations Density 0.459%

    No Known Activations