© 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
    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. 17299
    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
    ouble
    -0.68
     wedge
    -0.66
     lull
    -0.66
     denomination
    -0.64
     Mao
    -0.63
     evenly
    -0.63
    Sov
    -0.63
    ibrary
    -0.63
    ¬¼
    -0.62
    ĻĤ
    -0.62
    POSITIVE LOGITS
    ghost
    0.72
    Magikarp
    0.68
    Edited
    0.68
    ModLoader
    0.67
    ructose
    0.66
    thur
    0.66
    ORS
    0.65
    oreal
    0.64
    ursed
    0.64
    TH
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.