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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3667
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating the completion or fulfillment of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "complete" and its variations

    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
    maid
    -0.76
     whistleblowers
    -0.71
    adish
    -0.70
     Disciple
    -0.68
    */(
    -0.68
     dstg
    -0.67
    uay
    -0.67
     inh
    -0.63
    uyomi
    -0.63
    pload
    -0.63
    POSITIVE LOGITS
    teness
    0.94
    bred
    0.80
    complete
    0.79
    rehensive
    0.78
     fabrication
    0.78
     Rica
    0.73
     Complete
    0.73
     completes
    0.72
     fulfillment
    0.71
    izable
    0.70
    Activations Density 0.013%

    No Known Activations