© 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. 12-RES-JB
    11. 2282
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features related to computer hardware

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    features and benefits related to audio equipment and technology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     begg
    -0.75
    wives
    -0.72
     sometime
    -0.70
    arial
    -0.70
     payday
    -0.69
    ieg
    -0.67
    arie
    -0.66
     franc
    -0.65
     Spani
    -0.64
    uary
    -0.64
    POSITIVE LOGITS
     eliminates
    0.99
     optimized
    0.97
     patented
    0.96
    Dual
    0.94
     Provides
    0.93
     Ideal
    0.93
    Ultra
    0.92
    eaturing
    0.91
     ensures
    0.89
     seamlessly
    0.89
    Activations Density 0.556%

    No Known Activations