© 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. 24288
    Prev
    Next
    INDEX
    Explanations

    patterns related to categorization or segmentation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the division or categorization of content

    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
    dar
    -0.78
    press
    -0.75
     understatement
    -0.69
    aya
    -0.68
    inem
    -0.67
    tar
    -0.67
    iron
    -0.66
    eton
    -0.66
    eva
    -0.64
    ima
    -0.64
    POSITIVE LOGITS
     categories
    1.23
     manageable
    1.14
     subsections
    1.01
     segments
    1.01
     thirds
    1.01
     tiers
    1.00
     sections
    0.99
     phases
    0.98
     groups
    0.96
     smaller
    0.93
    Activations Density 0.104%

    No Known Activations