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. 8-RES-JB
    6. 16538
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "To"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rets
    -0.74
    pretty
    -0.67
    kind
    -0.65
    SpaceEngineers
    -0.63
    uments
    -0.63
    ãģł
    -0.62
    minster
    -0.61
    miss
    -0.60
    rage
    -0.59
    hest
    -0.59
    POSITIVE LOGITS
     researchers
    0.75
     psychologists
    0.69
     physicists
    0.69
     however
    0.69
     filmmakers
    0.67
     we
    0.67
     astronomers
    0.67
     moreover
    0.66
     Forbes
    0.66
     planners
    0.64
    Activations Density 0.215%

    No Known Activations