© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 23201
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to championships, accomplishments, and awards

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to champions, competition, and triumph 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-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
    0:0.04
    1:0.04
    2:0.17
    3:0.07
    4:0.08
    5:0.11
    6:0.03
    7:0.04
    8:0.11
    9:0.17
    10:0.06
    11:0.02
    Negative Logits
    azard
    -1.45
    edient
    -1.38
    azo
    -1.34
     GOODMAN
    -1.31
    ascript
    -1.30
    ysis
    -1.29
    ividual
    -1.25
    usercontent
    -1.24
    lasses
    -1.23
    abus
    -1.23
    POSITIVE LOGITS
     Targ
    1.34
     Fior
    1.32
     Ladies
    1.20
     Paw
    1.17
    iHUD
    1.17
     League
    1.14
     Mouse
    1.11
     bragging
    1.11
    Dialogue
    1.07
     Lich
    1.07
    Activations Density 0.017%

    No Known Activations