© 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. 16140
    Prev
    Next
    INDEX
    Explanations

    the occurrence of "left" in various contexts

    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
    0:0.02
    1:0.01
    2:0.31
    3:0.07
    4:0.06
    5:0.04
    6:0.01
    7:0.01
    8:0.27
    9:0.09
    10:0.02
    11:0.01
    Negative Logits
    SHIP
    -1.56
    MN
    -1.52
     Flavoring
    -1.48
    Plugin
    -1.46
    scl
    -1.41
     Cosponsors
    -1.37
    ��
    -1.35
    Map
    -1.34
    Stats
    -1.33
    Helper
    -1.32
    POSITIVE LOGITS
     voic
    1.60
     throats
    1.54
    azeera
    1.46
     Ruk
    1.41
     unfinished
    1.41
     laure
    1.39
     pockets
    1.36
     gaping
    1.34
     territory
    1.31
    ovych
    1.28
    Activations Density 0.044%

    No Known Activations