© 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. 12748
    Prev
    Next
    INDEX
    Explanations

    second person pronouns followed by expressions of knowing or seeing

    oai_token-act-pair · gpt-3.5-turbo

    references to the reader or audience

    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
    letters
    -0.75
    uca
    -0.70
    Reloaded
    -0.67
    Cra
    -0.63
    ¿½
    -0.62
    ospace
    -0.61
    OSP
    -0.60
     Third
    -0.59
     millenn
    -0.59
    HCR
    -0.58
    POSITIVE LOGITS
     guessed
    1.07
    'll
    1.00
    'd
    0.98
     might
    0.97
     know
    0.94
    're
    0.94
    've
    0.92
    tub
    0.91
     can
    0.89
     may
    0.88
    Activations Density 0.034%

    No Known Activations