© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 17173
    Prev
    Next
    INDEX
    Explanations

    items related to shopping or consumer products

    oai_token-act-pair · gpt-3.5-turbo

    items commonly associated with consumer goods and leisure activities

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Pwr
    -0.55
    hematically
    -0.44
    =-=-
    -0.43
    \/\/
    -0.43
     glim
    -0.41
    staking
    -0.41
     hindsight
    -0.41
    maxwell
    -0.41
    ptoms
    -0.41
    ensional
    -0.41
    POSITIVE LOGITS
    .).
    0.57
     etc
    0.54
    ?).
    0.49
     respectively
    0.48
    ).[
    0.47
    ).
    0.46
     fame
    0.46
    )."
    0.45
    !).
    0.44
     thereof
    0.42
    Activations Density 4.667%

    No Known Activations