© 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. 24306
    Prev
    Next
    INDEX
    Explanations

    phrases related to facing challenges or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the concept of "in the face of" followed by a challenge or opposition

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    igue
    -0.88
    leave
    -0.73
    inet
    -0.67
    iaries
    -0.66
    dot
    -0.66
    knit
    -0.65
    ards
    -0.65
    most
    -0.64
    leground
    -0.64
    oor
    -0.64
    POSITIVE LOGITS
     advancing
    0.73
     Hurricane
    0.69
     completing
    0.69
     hindsight
    0.69
     achieving
    0.68
    interstitial
    0.67
     facilitating
    0.66
     either
    0.66
     those
    0.65
     increasing
    0.65
    Activations Density 0.231%

    No Known Activations