© 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. 2-RES-JB
    11. 21196
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high level of completion or finality

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "complete" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maid
    -0.82
    uay
    -0.70
    adish
    -0.69
     dstg
    -0.67
     whistleblowers
    -0.65
    ean
    -0.65
    dayName
    -0.61
     Disciple
    -0.61
    iggurat
    -0.60
    hare
    -0.60
    POSITIVE LOGITS
    teness
    0.86
    bred
    0.86
     fabrication
    0.76
    rehensive
    0.74
    izable
    0.72
     fulfillment
    0.70
     Rica
    0.70
    TAIN
    0.67
     annihilation
    0.65
     playthrough
    0.65
    Activations Density 0.014%

    No Known Activations