© 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. 9-RES-JB
    11. 19803
    Prev
    Next
    INDEX
    Explanations

    references to specific years or dates, especially the year 2010

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 2010 and related statistics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    onite
    -0.76
    phy
    -0.74
    ube
    -0.73
    amins
    -0.71
     ancest
    -0.66
    inic
    -0.66
    pill
    -0.65
    eers
    -0.63
    inates
    -0.63
    lihood
    -0.62
    POSITIVE LOGITS
    å¹
    1.02
    -'
    0.89
     onwards
    0.87
     census
    0.74
     Census
    0.72
     onward
    0.69
    iversary
    0.65
    acious
    0.64
    âĢ²
    0.64
    天
    0.62
    Activations Density 0.067%

    No Known Activations