© 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. 8-RES-JB
    11. 1963
    Prev
    Next
    INDEX
    Explanations

    conjunctions "but" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "but" used to contrast or qualify previous statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yn
    -0.68
    reen
    -0.68
    \":
    -0.67
    esc
    -0.66
    Ñı
    -0.65
    obyl
    -0.64
    idan
    -0.64
    avour
    -0.61
    agan
    -0.61
    ENG
    -0.61
    POSITIVE LOGITS
     nevertheless
    1.09
     nonetheless
    0.96
     hey
    0.96
     alas
    0.93
    tons
    0.89
     fortunately
    0.78
    chers
    0.76
     beware
    0.76
     suffice
    0.75
     surely
    0.74
    Activations Density 0.147%

    No Known Activations