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. 10-RES-JB
    6. 19225
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "want" with various levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire and intention

    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
    NVIDIA
    -0.62
    ilings
    -0.61
    livious
    -0.58
    ulty
    -0.58
    illian
    -0.57
     obser
    -0.57
    ielding
    -0.57
    icol
    -0.56
    hesis
    -0.55
    usting
    -0.55
    POSITIVE LOGITS
     to
    1.10
     revenge
    1.03
     nothing
    0.90
    only
    0.87
     vengeance
    0.86
     answers
    0.80
     permission
    0.75
    to
    0.75
    reprene
    0.75
     something
    0.73
    Activations Density 0.111%

    No Known Activations