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. 6359
    Prev
    Next
    INDEX
    Explanations

    instances where the text presents a counterpoint or contrast to an idea

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but," often used to introduce contrasting ideas or exceptions

    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
    uto
    -0.68
    irl
    -0.65
    amus
    -0.64
    Times
    -0.63
    edu
    -0.62
    ige
    -0.62
    awan
    -0.62
    ories
    -0.61
    hal
    -0.60
    leck
    -0.59
    POSITIVE LOGITS
     alas
    1.26
     nevertheless
    1.25
     nonetheless
    1.16
     fortunately
    1.06
     luckily
    0.99
    tons
    0.93
    chery
    0.92
     ultimately
    0.92
     hey
    0.91
     unfortunately
    0.86
    Activations Density 0.190%

    No Known Activations