Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 8083
    Prev
    Next
    INDEX
    Explanations

    words related to energy or power

    oai_token-act-pair · gpt-3.5-turbo

    words and terms related to energy and its various forms or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Victims
    -0.63
     lap
    -0.61
    Mah
    -0.60
     Marriage
    -0.57
     Editors
    -0.56
     Kidd
    -0.56
     Customs
    -0.56
     translating
    -0.55
     swirling
    -0.55
     Prison
    -0.55
    POSITIVE LOGITS
    ener
    1.31
    getic
    0.96
    iatus
    0.91
     guiActiveUn
    0.88
    rors
    0.85
    oneliness
    0.80
    ãĥ´ãĤ¡
    0.80
    aution
    0.80
    peror
    0.79
    onite
    0.79
    Activations Density 0.011%

    No Known Activations