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. 6-RES-JB
    6. 11319
    Prev
    Next
    INDEX
    Explanations

    instances where the conjunction "though" is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "though," indicating contrasting or qualifying statements

    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
    lees
    -0.81
    anu
    -0.70
    asus
    -0.70
    oire
    -0.69
    pta
    -0.67
    isible
    -0.67
    atos
    -0.65
    cup
    -0.65
    enter
    -0.65
    ãĥĻ
    -0.63
    POSITIVE LOGITS
     admittedly
    0.97
     fortunately
    0.91
     thankfully
    0.89
     curiously
    0.83
     interestingly
    0.80
    tons
    0.79
     luckily
    0.78
     acknowledging
    0.73
     oddly
    0.73
     nonetheless
    0.72
    Activations Density 0.033%

    No Known Activations