© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7722
    Prev
    Next
    INDEX
    Explanations

    instances of the word "but" followed by expressions of interest or consideration

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "can't help but" and its variations indicating inevitability or compulsion

    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
    Offline
    -0.69
     clipboard
    -0.67
    ories
    -0.64
    ipment
    -0.63
    endar
    -0.63
     Expedition
    -0.62
     centr
    -0.62
    ftime
    -0.62
    built
    -0.61
    terday
    -0.61
    POSITIVE LOGITS
     tease
    0.79
     breathe
    0.73
     grin
    0.71
    TEXTURE
    0.67
     refrain
    0.66
    itely
    0.64
    Lago
    0.63
     inh
    0.63
     capitalize
    0.63
    EMBER
    0.63
    Activations Density 0.058%

    No Known Activations