© 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. 1-RES-JB
    11. 20841
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Would" or "Does"

    oai_token-act-pair · gpt-3.5-turbo

    interrogative phrases, particularly those beginning with "Would" or "Does."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.81
    á½
    -0.76
    keyes
    -0.68
    bleacher
    -0.68
    çĦ
    -0.67
    rooms
    -0.66
    ãĥĥãĥĪ
    -0.65
    é¾
    -0.64
    о
    -0.64
    ulated
    -0.62
    POSITIVE LOGITS
     Does
    0.86
     Would
    0.81
    yip
    0.81
    soever
    0.78
     Have
    0.77
     Exactly
    0.76
     Didn
    0.76
     Anyone
    0.74
    terday
    0.74
    linger
    0.73
    Activations Density 0.013%

    No Known Activations