© 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. 2-RES-JB
    6. 17701
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hma
    -0.75
     Dalai
    -0.74
    ĸļ
    -0.72
     Pyth
    -0.65
     htt
    -0.65
    ply
    -0.65
     Notting
    -0.65
     fingert
    -0.64
    ĨĴ
    -0.63
     ingred
    -0.63
    POSITIVE LOGITS
    cake
    0.93
    capacity
    0.72
     Apply
    0.70
     COUN
    0.70
    cakes
    0.68
    Fight
    0.65
    deal
    0.64
    falls
    0.64
    /(
    0.64
    shadow
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.