Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21938
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'but' being used in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "but" and related phrases 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
    incial
    -0.70
    result
    -0.70
    adr
    -0.66
    oufl
    -0.64
    ocative
    -0.63
    built
    -0.63
    edu
    -0.62
    iosyncr
    -0.61
    naire
    -0.61
    èĢħ
    -0.61
    POSITIVE LOGITS
     hey
    1.42
     alas
    1.26
     yeah
    1.22
     luckily
    1.11
     nevertheless
    1.08
     nonetheless
    1.07
    tons
    1.07
     suffice
    1.06
     congr
    1.06
     damn
    1.01
    Activations Density 0.148%

    No Known Activations