© 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. 9-RES-JB
    11. 4874
    Prev
    Next
    INDEX
    Explanations

    the conjunction "But" at the beginning of sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "But."

    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
    interstitial
    -0.66
    Roaming
    -0.65
    adr
    -0.64
    spir
    -0.62
    velop
    -0.60
    derived
    -0.60
    Increased
    -0.59
    guard
    -0.59
    abilities
    -0.58
    igators
    -0.57
    POSITIVE LOGITS
    tons
    1.52
     hey
    1.40
     alas
    1.37
     yeah
    1.21
    tery
    1.07
     anyways
    1.07
     wait
    1.03
     luckily
    1.02
     anyway
    0.98
     THEN
    0.95
    Activations Density 0.145%

    No Known Activations