© 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. 8-RES-JB
    11. 12894
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "However"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "However."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    gio
    -0.56
    kamp
    -0.56
    letter
    -0.55
     âĢİ
    -0.55
     triangle
    -0.53
     centre
    -0.53
     Appropriations
    -0.53
    parent
    -0.50
    rieg
    -0.50
    abies
    -0.49
    POSITIVE LOGITS
     importantly
    0.74
    chers
    0.73
    .,
    0.70
     interestingly
    0.70
    lers
    0.70
    ,.
    0.70
    terday
    0.69
    chery
    0.69
    tons
    0.69
    tif
    0.67
    Activations Density 0.046%

    No Known Activations