© 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. 21443
    Prev
    Next
    INDEX
    Explanations

    references to music, music production, and related concepts in various contexts

    oai_token-act-pair · gpt-4o-mini
    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
    0:0.06
    1:0.04
    2:0.21
    3:0.06
    4:0.04
    5:0.09
    6:0.02
    7:0.04
    8:0.05
    9:0.25
    10:0.06
    11:0.03
    Negative Logits
    assian
    -1.34
    Args
    -1.32
     Prosecut
    -1.32
    ctive
    -1.31
     Orders
    -1.29
    iHUD
    -1.28
    ierre
    -1.28
    kw
    -1.26
    ��
    -1.26
    ウス
    -1.26
    POSITIVE LOGITS
     Beyon
    1.44
    ophon
    1.41
    geist
    1.35
     glam
    1.29
     laun
    1.25
     DJs
    1.25
    mercial
    1.21
     Moonlight
    1.19
     streamed
    1.18
     grape
    1.17
    Activations Density 0.048%

    No Known Activations