© 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. 10222
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating a relationship between two quantities, such as "the more...the higher."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a correlation or relationship between two variables

    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
    edit
    -0.71
    opian
    -0.68
    istani
    -0.67
    external
    -0.66
    usa
    -0.65
    cedes
    -0.65
    enny
    -0.65
    wart
    -0.64
    ials
    -0.63
    ftime
    -0.63
    POSITIVE LOGITS
     better
    1.23
     harder
    1.12
     easier
    1.08
     worse
    1.06
     sooner
    1.06
     greater
    1.06
     stronger
    1.04
     safer
    1.01
     healthier
    1.01
     clearer
    1.00
    Activations Density 0.046%

    No Known Activations