© 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. 11-RES-JB
    11. 12813
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a quantity or proportion of a group

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the pattern "many of" or related constructions indicating quantities or groups

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ovember
    -0.75
    ablishment
    -0.70
     lineback
    -0.57
     Suppose
    -0.55
    uden
    -0.55
     EVENTS
    -0.54
     rematch
    -0.54
    aeda
    -0.52
     respons
    -0.52
    REL
    -0.51
    POSITIVE LOGITS
     whom
    1.99
     which
    1.45
     them
    1.44
     whose
    1.33
    whose
    1.19
    which
    1.09
     Them
    1.04
     THEM
    1.03
    them
    0.92
    Which
    0.87
    Activations Density 0.083%

    No Known Activations