© 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. 0-RES-JB
    11. 602
    Prev
    Next
    INDEX
    Explanations

    interrogative sentences starting with the word "Does"

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "Does."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     closing
    -0.68
     dispatch
    -0.66
     opening
    -0.65
     closed
    -0.64
     launch
    -0.64
     open
    -0.63
     barric
    -0.62
     lead
    -0.61
     kick
    -0.61
     stand
    -0.60
    POSITIVE LOGITS
     Does
    3.01
    Does
    2.56
     Doesn
    2.10
    does
    2.06
     DOES
    1.74
     Did
    1.69
     Isn
    1.57
     Would
    1.52
     Is
    1.50
     Makes
    1.48
    Activations Density 0.015%

    No Known Activations