© 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. 7-RES-JB
    11. 2180
    Prev
    Next
    INDEX
    Explanations

    sentences containing contrasting statements or ideas

    oai_token-act-pair · gpt-3.5-turbo

    the word "but" to indicate contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roy
    -0.85
    oys
    -0.75
    oun
    -0.71
    ump
    -0.69
    itto
    -0.69
    osite
    -0.68
    uddin
    -0.68
    ands
    -0.66
    oop
    -0.65
    asar
    -0.64
    POSITIVE LOGITS
    tons
    1.05
     alas
    1.04
     nevertheless
    1.03
     nonetheless
    0.99
     fortunately
    0.91
     luckily
    0.90
     beware
    0.83
     insofar
    0.82
     hey
    0.80
     unfortunately
    0.76
    Activations Density 0.177%

    No Known Activations