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. 3-RES-JB
    6. 21505
    Prev
    Next
    INDEX
    Explanations

    conjunctions signaling contrast

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" indicating contrasts or exceptions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agra
    -0.72
    roy
    -0.71
    uto
    -0.69
    analysis
    -0.67
    oin
    -0.66
    ump
    -0.66
    ige
    -0.65
    entry
    -0.65
    velt
    -0.64
    edu
    -0.64
    POSITIVE LOGITS
     alas
    1.09
    tons
    1.07
     nevertheless
    1.05
    chery
    0.98
     luckily
    0.96
     fortunately
    0.95
     nonetheless
    0.94
     hey
    0.90
     thankfully
    0.83
     unfortunately
    0.83
    Activations Density 0.230%

    No Known Activations