© 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. 12761
    Prev
    Next
    INDEX
    Explanations

    instances where possessive pronouns are followed by a word

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ownership or possession

    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
    river
    -0.75
     [];
    -0.73
    ¿
    -0.70
    Transfer
    -0.68
    thood
    -0.67
    rentice
    -0.67
    icably
    -0.67
    eta
    -0.65
    ocument
    -0.64
    oval
    -0.64
    POSITIVE LOGITS
     own
    1.38
     sights
    1.33
     ups
    1.12
     doubts
    1.09
     faults
    1.03
     detractors
    1.01
     roots
    0.96
     reasons
    0.96
     strengths
    0.96
     fingerprints
    0.96
    Activations Density 0.065%

    No Known Activations