© 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. 39474
    Prev
    Next
    INDEX
    Explanations

    instances of collaboration and cooperative efforts in various contexts

    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
    2:0.07
    3:0.07
    4:0.10
    5:0.02
    6:0.03
    7:0.32
    8:0.02
    9:0.03
    10:0.13
    11:0.13
    Negative Logits
    inventoryQuantity
    -1.45
    meter
    -1.36
    hell
    -1.34
    BuyableInstoreAndOnline
    -1.26
    reflect
    -1.26
     sails
    -1.24
    oubt
    -1.23
    stakes
    -1.22
    tube
    -1.21
    etsy
    -1.20
    POSITIVE LOGITS
     arrang
    1.39
     linem
    1.35
     strateg
    1.31
    iblings
    1.30
    ournal
    1.26
     collaborators
    1.26
    ──
    1.24
     Grizz
    1.21
    rw
    1.20
    venture
    1.20
    Activations Density 0.010%

    No Known Activations