© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 11382
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or activities that are taking place or will or have taken place

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.12
    3:0.11
    4:0.23
    5:0.05
    6:0.04
    7:0.02
    8:0.10
    9:0.13
    10:0.06
    11:0.02
    Negative Logits
     opportunity
    -1.39
     opportunities
    -1.38
     chance
    -1.26
     bandwagon
    -1.20
    estern
    -1.19
    reviewed
    -1.18
    started
    -1.18
     whiff
    -1.17
     chances
    -1.16
     circulation
    -1.11
    POSITIVE LOGITS
     Pixie
    1.33
    姫
    1.32
    ���
    1.32
     Azerb
    1.30
     Ancients
    1.29
    ��
    1.27
    ゴン
    1.27
     Myr
    1.27
    ctica
    1.26
    itatively
    1.25
    Activations Density 0.017%

    No Known Activations