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. 6-RES-JB
    6. 1979
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses that emphasize a particular point or statement

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rior
    -0.62
     downs
    -0.58
    Luck
    -0.56
    kamp
    -0.56
    ãĥ¬
    -0.54
    ysis
    -0.54
     mull
    -0.54
    english
    -0.53
     Legend
    -0.53
    Guard
    -0.52
    POSITIVE LOGITS
     fateful
    0.85
     same
    0.76
    cher
    0.74
     pesky
    0.71
    chers
    0.70
     latter
    0.69
    same
    0.65
    iago
    0.62
    interstitial
    0.62
     occurred
    0.61
    Activations Density 0.311%

    No Known Activations