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

    Neuronpedia

    Jacobian LensNEW
    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. 20779
    Prev
    Next
    INDEX
    Explanations

    contrasting statements that feature the word "but"

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that introduce contrasting or adversative statements

    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
    dayName
    -0.73
    abe
    -0.71
    \":
    -0.71
    AU
    -0.70
    onomy
    -0.69
    sylvania
    -0.68
    )|
    -0.67
    orts
    -0.66
    endar
    -0.65
    kamp
    -0.64
    POSITIVE LOGITS
    tons
    1.34
     alas
    1.22
    chers
    0.98
     luckily
    0.90
     hey
    0.90
     somehow
    0.88
     fortunately
    0.87
     unfortunately
    0.86
     beware
    0.85
     mirac
    0.85
    Activations Density 0.279%

    No Known Activations