© 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. 20526
    Prev
    Next
    INDEX
    Explanations

    names or references related to people and entities

    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
    0:0.04
    1:0.42
    2:0.02
    3:0.03
    4:0.02
    5:0.21
    6:0.03
    7:0.01
    8:0.03
    9:0.07
    10:0.04
    11:0.03
    Negative Logits
     sqor
    -2.02
     indist
    -1.92
    accompan
    -1.80
     GOODMAN
    -1.78
     Canad
    -1.72
     Feder
    -1.70
    rawdownloadcloneembedreportprint
    -1.70
     independ
    -1.64
     Independence
    -1.61
    ATIONAL
    -1.59
    POSITIVE LOGITS
    z
    2.92
    zan
    2.46
    zynski
    2.32
    zes
    2.31
    zh
    2.29
    zik
    2.27
    zone
    2.25
    Z
    2.19
    zos
    2.19
    zel
    2.14
    Activations Density 0.029%

    No Known Activations