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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 19936
    Prev
    Next
    INDEX
    Explanations

    words related to religious or ceremonial significance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sacrilege and sacredness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DonaldTrump
    -0.77
    ously
    -0.74
    è¦ļéĨĴ
    -0.71
    icans
    -0.68
     Clarkson
    -0.66
     Sutherland
    -0.63
    makers
    -0.63
     Roosevelt
    -0.63
    ãĤ¤ãĥĪ
    -0.62
     Jacket
    -0.62
    POSITIVE LOGITS
    char
    1.30
    rament
    1.29
    rifice
    1.23
    rast
    1.03
    het
    1.02
    erd
    1.02
    ros
    1.01
    raf
    0.97
    ram
    0.96
    stant
    0.96
    Activations Density 0.028%

    No Known Activations