© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 24300
    Prev
    Next
    INDEX
    Explanations

    the word "but" along with contrasting information

    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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tained
    -0.78
    verted
    -0.77
    illus
    -0.76
    interstitial
    -0.76
    galitarian
    -0.75
    colored
    -0.75
    ãģĨ
    -0.75
    uphem
    -0.74
    umat
    -0.74
    ictionary
    -0.72
    POSITIVE LOGITS
     realistically
    1.14
     alas
    1.10
     ideally
    1.05
     unless
    1.03
     barring
    1.03
     hopefully
    0.98
     meantime
    0.92
     fortunately
    0.91
     chances
    0.91
     sooner
    0.90
    Activations Density 0.251%

    No Known Activations