© 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. 1-RES-JB
    11. 20443
    Prev
    Next
    INDEX
    Explanations

    references to extreme points or levels, such as highs and lows

    oai_token-act-pair · gpt-3.5-turbo

    references to extremes in experiences, particularly highs and lows

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Fac
    -0.79
    Austral
    -0.77
    shapeshifter
    -0.76
    Tour
    -0.73
    Shell
    -0.72
    ATA
    -0.70
    HOU
    -0.70
    Translation
    -0.70
    Department
    -0.68
    OTS
    -0.68
    POSITIVE LOGITS
     highs
    1.38
     lows
    1.28
    terday
    1.09
    terness
    0.96
     heights
    0.92
     horizont
    0.88
    poons
    0.84
    mith
    0.84
     Seym
    0.82
    ilight
    0.81
    Activations Density 0.010%

    No Known Activations