© 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. 17216
    Prev
    Next
    INDEX
    Explanations

    phrases related to complexity, boundaries, and sophisticated designs

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases associated with intense emotional experiences and complex interactions

    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
     Atlantis
    -0.49
     Twain
    -0.45
     Pett
    -0.44
    exempt
    -0.44
    dL
    -0.44
     Beir
    -0.42
     Marriott
    -0.42
    activated
    -0.41
     Lafayette
    -0.41
     Wilkinson
    -0.41
    POSITIVE LOGITS
    Reviewer
    0.58
     âĢº
    0.53
    etheless
    0.52
    catentry
    0.49
    taboola
    0.47
    ounters
    0.45
    bender
    0.44
    merce
    0.43
    smanship
    0.42
    kid
    0.42
    Activations Density 2.771%

    No Known Activations