© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17104
    Prev
    Next
    INDEX
    Explanations

    contrasting relationships or distinctions between concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but" indicating contrastive statements

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

    No Comments

    Negative Logits
    uters
    -0.79
    uter
    -0.77
    unction
    -0.76
    minent
    -0.74
    roy
    -0.74
    velt
    -0.72
    alty
    -0.72
    enter
    -0.71
    uther
    -0.71
    ct
    -0.70
    POSITIVE LOGITS
     nor
    0.99
     suffice
    0.92
     nevertheless
    0.85
     alas
    0.80
     rather
    0.78
     merely
    0.78
     luckily
    0.77
     hey
    0.76
     fortunately
    0.75
    chery
    0.75
    Activations Density 0.105%

    No Known Activations