© 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. 4-RES-JB
    11. 20834
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to the organization or entity abbreviated as "AF."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Blackwell
    -0.81
     Heller
    -0.75
     Muller
    -0.72
     Morg
    -0.71
     Kessler
    -0.70
     Vaugh
    -0.70
     Boone
    -0.70
     McKenna
    -0.69
     MLG
    -0.69
    igators
    -0.68
    POSITIVE LOGITS
    RIC
    1.20
    amily
    1.08
    SPA
    1.06
    ornia
    1.03
    onso
    0.99
    rica
    0.98
    lesh
    0.92
    chieve
    0.91
    rost
    0.91
    rican
    0.89
    Activations Density 0.008%

    No Known Activations