© 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. 3-RES-JB
    11. 16918
    Prev
    Next
    INDEX
    Explanations

    commands or instructions with a focus on showing or checking something

    oai_token-act-pair · gpt-3.5-turbo

    references to actionable advice or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    division
    -0.53
    communication
    -0.45
    marine
    -0.45
    products
    -0.42
    atur
    -0.41
    frac
    -0.41
    ËĪ
    -0.39
     carrier
    -0.39
    alist
    -0.39
    )",
    -0.39
    POSITIVE LOGITS
     however
    0.64
     ital
    0.57
     meanwhile
    0.51
     furthermore
    0.47
    emonium
    0.47
     therefore
    0.47
     moreover
    0.46
    zbek
    0.45
    sonian
    0.45
     Nek
    0.45
    Activations Density 2.190%

    No Known Activations