© 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. 12767
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a person's age

    oai_token-act-pair · gpt-3.5-turbo

    numerical age references associated with people or players

    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
     Rao
    -0.67
     Lis
    -0.66
     Gupta
    -0.65
    isol
    -0.65
     Empress
    -0.63
     Administrator
    -0.62
     Vik
    -0.61
     Mandal
    -0.60
     Queen
    -0.59
     Malaysia
    -0.58
    POSITIVE LOGITS
    rafted
    1.06
     games
    0.90
     tackles
    0.86
     undrafted
    0.85
     carries
    0.84
     stitches
    0.82
    olphins
    0.81
    Height
    0.81
    ers
    0.80
     seasons
    0.80
    Activations Density 0.083%

    No Known Activations