© 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. 6-RES-JB
    11. 20589
    Prev
    Next
    INDEX
    Explanations

    the word "although" that signals a contrast in the text

    oai_token-act-pair · gpt-3.5-turbo

    the word "although" and its various repetitions, 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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entry
    -0.74
    hal
    -0.74
    enter
    -0.74
    lees
    -0.69
    oire
    -0.69
    elle
    -0.68
    unes
    -0.68
    ath
    -0.68
    Bas
    -0.67
    edu
    -0.67
    POSITIVE LOGITS
     admittedly
    0.91
     fortunately
    0.86
     interestingly
    0.81
     acknowledging
    0.80
    chery
    0.80
     technically
    0.79
    tons
    0.78
     luckily
    0.78
     nevertheless
    0.75
     retaining
    0.75
    Activations Density 0.037%

    No Known Activations