© 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. 11-RES-JB
    6. 21848
    Prev
    Next
    INDEX
    Explanations

    numeric values with some symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to specifications and nutritional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /+
    -0.72
    edin
    -0.67
    >:
    -0.66
    thur
    -0.66
    !/
    -0.65
    itored
    -0.64
    ngth
    -0.62
    ti
    -0.61
    rys
    -0.61
    wx
    -0.60
    POSITIVE LOGITS
     Elim
    0.93
     Medals
    0.78
     DevOnline
    0.77
     Deaths
    0.76
     Obj
    0.74
     Nemesis
    0.70
     Dust
    0.70
     Achievements
    0.69
     Cassidy
    0.68
     Haku
    0.67
    Activations Density 0.074%

    No Known Activations