© 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. 11518
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of being "outside" or external

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "outside" or external environments

    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
    netflix
    -0.79
    orah
    -0.76
    enegger
    -0.74
    lication
    -0.71
    ony
    -0.70
    hered
    -0.70
    lde
    -0.69
    arrell
    -0.69
    amaz
    -0.69
    apa
    -0.67
    POSITIVE LOGITS
     observer
    0.97
     linebacker
    0.94
     linebackers
    0.90
     world
    0.85
     workings
    0.75
     influences
    0.73
     observers
    0.73
     edge
    0.72
     scoop
    0.72
     edges
    0.72
    Activations Density 0.038%

    No Known Activations