© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 15028
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive terms that convey qualities or characteristics of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.04
    3:0.18
    4:0.03
    5:0.04
    6:0.19
    7:0.04
    8:0.02
    9:0.02
    10:0.16
    11:0.17
    Negative Logits
     Hedge
    -2.68
     Founders
    -2.53
     Queens
    -2.39
     Waves
    -2.31
     Unicorn
    -2.27
     Doodle
    -2.25
     ambassadors
    -2.24
     Lans
    -2.22
     Bridge
    -2.21
     Gideon
    -2.21
    POSITIVE LOGITS
    ────────
    2.52
    cook
    2.48
    ────
    2.43
    å
    2.40
     (−
    2.38
    †
    2.35
     radioactive
    2.32
    ctor
    2.27
    Camp
    2.27
     deflation
    2.26
    Activations Density 0.004%

    No Known Activations