© 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. 25034
    Prev
    Next
    INDEX
    Explanations

    numerical values and results related to games or competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.03
    2:0.07
    3:0.07
    4:0.07
    5:0.04
    6:0.05
    7:0.05
    8:0.04
    9:0.07
    10:0.27
    11:0.10
    Negative Logits
     Editors
    -1.73
    netflix
    -1.63
    erala
    -1.60
    onym
    -1.58
    anthrop
    -1.56
     mourning
    -1.55
     Forensic
    -1.54
    CTV
    -1.52
     Flavoring
    -1.52
     accredited
    -1.51
    POSITIVE LOGITS
    speed
    1.55
     bounce
    1.54
    �
    1.51
     initiating
    1.45
     mismatch
    1.42
    assert
    1.41
    defense
    1.38
     cascade
    1.35
     grabs
    1.34
     ensued
    1.32
    Activations Density 0.002%

    No Known Activations