© 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. 3-RES-JB
    11. 17254
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Ãľ
    -0.75
    etheless
    -0.69
     Tinder
    -0.69
     Mines
    -0.67
     brushes
    -0.67
    ldon
    -0.66
     Colo
    -0.66
    utenberg
    -0.65
     Calais
    -0.65
     conclud
    -0.64
    POSITIVE LOGITS
    AAA
    0.88
    lesiastical
    0.86
    ran
    0.85
    ³³³³³³³³³³³³³³³³
    0.83
    Av
    0.79
    SA
    0.79
    oor
    0.78
    HA
    0.78
    Adv
    0.76
    CLA
    0.76
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.