© 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. 14495
    Prev
    Next
    INDEX
    Explanations

    contrasting statements or contradictory ideas

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" indicating a contrast or exception in statements

    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
    roy
    -0.76
    million
    -0.67
    ories
    -0.66
    amus
    -0.64
    Tube
    -0.63
    oire
    -0.62
    irt
    -0.62
    irm
    -0.62
    built
    -0.61
    ãĤµ
    -0.61
    POSITIVE LOGITS
     nevertheless
    1.30
     nonetheless
    1.27
     alas
    1.22
    tons
    1.12
     luckily
    1.04
     hey
    1.03
     fortunately
    1.03
    chery
    0.92
     suffice
    0.92
     thankfully
    0.89
    Activations Density 0.202%

    No Known Activations