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. 0-RES-JB
    6. 23673
    Prev
    Next
    INDEX
    Explanations

    elements that are related to "cosmos", which may refer to various contexts such as medical, sports, and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to "cos" or "cosmetics."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ber
    -0.63
     muzzle
    -0.63
     pinned
    -0.62
     disbanded
    -0.61
     checkpoint
    -0.61
     sentences
    -0.61
     bullet
    -0.60
     tied
    -0.60
     Merrill
    -0.60
     trails
    -0.59
    POSITIVE LOGITS
    cos
    4.65
    Cos
    2.21
    kos
    1.52
    co
    1.41
     cos
    1.41
     Cos
    1.38
    sin
    1.31
    cas
    1.18
    cor
    1.15
    cone
    1.14
    Activations Density 0.011%

    No Known Activations