Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 2369
    Prev
    Next
    INDEX
    Explanations

    words related to completion or fullness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "complete."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maid
    -0.90
    uay
    -0.74
     dstg
    -0.69
    hots
    -0.66
     cents
    -0.65
     Fet
    -0.64
     Cosponsors
    -0.64
     microphones
    -0.63
    worn
    -0.62
    uds
    -0.62
    POSITIVE LOGITS
    teness
    0.96
    bred
    0.87
     fabrication
    0.80
    rehensive
    0.79
     fulfillment
    0.73
     annihilation
    0.71
     playthrough
    0.70
     completion
    0.70
    issance
    0.70
     elimination
    0.69
    Activations Density 0.018%

    No Known Activations