© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 22171
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    immune
    -0.74
    enic
    -0.73
    enary
    -0.70
    opal
    -0.66
    inous
    -0.65
    elaide
    -0.65
    vantage
    -0.63
    eatured
    -0.63
    ERC
    -0.62
     shields
    -0.62
    POSITIVE LOGITS
     Fargo
    0.70
     skelet
    0.69
     Tiffany
    0.65
    Ħ¢
    0.65
     Saban
    0.65
     Fourth
    0.64
     respecting
    0.62
     Krist
    0.62
     Kyr
    0.62
     Saiyan
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.