© 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. 5-ATT-KK
    11. 39596
    Prev
    Next
    INDEX
    Explanations

    terms related to the Arctic and Antarctic regions, particularly focusing on ice, its conditions, and related research

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.04
    4:0.04
    5:0.04
    6:0.31
    7:0.03
    8:0.04
    9:0.04
    10:0.15
    11:0.14
    Negative Logits
    ruary
    -1.24
     Sole
    -1.21
     Anonymous
    -1.21
     [&
    -1.16
    MpServer
    -1.14
     Wally
    -1.13
     sow
    -1.13
     Orc
    -1.10
     Tik
    -1.10
     acet
    -1.10
    POSITIVE LOGITS
    philis
    1.43
    reements
    1.28
    ��
    1.27
    unctions
    1.26
    clerosis
    1.22
    �
    1.20
    onductor
    1.19
    itals
    1.19
    colm
    1.18
    riages
    1.18
    Activations Density 0.002%

    No Known Activations