© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 18302
    Prev
    Next
    INDEX
    Explanations

    details related to rules or guidelines

    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
    0:0.03
    1:0.01
    2:0.14
    3:0.06
    4:0.09
    5:0.09
    6:0.03
    7:0.03
    8:0.07
    9:0.10
    10:0.15
    11:0.13
    Negative Logits
     Founder
    -0.99
     blogger
    -0.94
     fut
    -0.92
     Doodle
    -0.91
    folk
    -0.90
    ypes
    -0.88
     bestselling
    -0.88
    apego
    -0.88
     Coup
    -0.87
     cryptocurrency
    -0.87
    POSITIVE LOGITS
     perpend
    1.30
     perpendicular
    1.26
     whereas
    1.26
     whence
    1.25
     preferably
    1.21
    ifice
    1.13
     angled
    1.13
     unless
    1.12
     whichever
    1.09
     protr
    1.07
    Activations Density 0.313%

    No Known Activations