© 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. 9-RES-JB
    11. 14771
    Prev
    Next
    INDEX
    Explanations

    conjunctions, especially 'but'

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" indicating contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ©
    -0.76
    ãĥĩ
    -0.71
    äºĶ
    -0.68
    null
    -0.67
    QB
    -0.66
    çĶ°
    -0.63
    iosyncr
    -0.62
    MY
    -0.60
    unit
    -0.60
    pid
    -0.59
    POSITIVE LOGITS
     nevertheless
    1.34
     nonetheless
    1.24
     anecd
    1.03
     luckily
    0.98
     hey
    0.94
     suffice
    0.87
     fortunately
    0.85
     Cathy
    0.72
     plenty
    0.69
     thanks
    0.68
    Activations Density 0.271%

    No Known Activations