© 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. 0-RES-JB
    11. 5289
    Prev
    Next
    INDEX
    Explanations

    verbs related to revitalizing or rejuvenating something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reinforcement and peripheral aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pow
    -0.89
     pow
    -0.76
    laws
    -0.69
    iage
    -0.69
    weet
    -0.68
     Harriet
    -0.65
    tnc
    -0.64
     theoret
    -0.64
     recomm
    -0.64
     USDA
    -0.62
    POSITIVE LOGITS
    orate
    2.79
     peripheral
    2.61
     peripher
    2.24
     periphery
    1.59
    ricular
    1.43
    ipher
    1.34
    aldi
    1.31
    acular
    1.01
    uras
    0.94
     placebo
    0.88
    Activations Density 0.032%

    No Known Activations