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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 12045
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs commonly used in descriptive or argumentative texts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.05
    2:0.05
    3:0.06
    4:0.03
    5:0.05
    6:0.13
    7:0.13
    8:0.04
    9:0.06
    10:0.18
    11:0.10
    Negative Logits
    )."
    -1.06
    '"
    -0.89
    ."[
    -0.88
    .'"
    -0.85
    )"
    -0.85
    ".[
    -0.83
    "'
    -0.82
    ".
    -0.79
    "(
    -0.78
     wink
    -0.78
    POSITIVE LOGITS
    WAR
    0.84
    ozyg
    0.83
    afety
    0.83
    elist
    0.81
     Roose
    0.78
    AUT
    0.77
    estern
    0.77
    \":
    0.76
    DragonMagazine
    0.74
    Arcade
    0.73
    Activations Density 0.616%

    No Known Activations