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. 8653
    Prev
    Next
    INDEX
    Explanations

    words related to promises or commitments

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "promote."

    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
     fault
    -0.67
     mund
    -0.66
     wait
    -0.63
    SEE
    -0.61
     fashioned
    -0.60
     scissors
    -0.59
     screws
    -0.59
    Fine
    -0.58
    lihood
    -0.58
     bugs
    -0.57
    POSITIVE LOGITS
    etheus
    1.63
    otional
    1.52
    inent
    1.50
    otions
    1.47
    inently
    1.35
    oter
    1.31
    otion
    1.31
    oted
    1.29
    inence
    1.29
    ises
    1.29
    Activations Density 0.017%

    No Known Activations