© 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. 10-ATT-KK
    11. 13707
    Prev
    Next
    INDEX
    Explanations

    references to events and announcements related to tournaments in the gaming community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.07
    2:0.11
    3:0.05
    4:0.05
    5:0.02
    6:0.06
    7:0.08
    8:0.04
    9:0.04
    10:0.20
    11:0.05
    Negative Logits
     Dian
    -3.66
     Cr
    -3.51
     Murd
    -3.17
     Budd
    -3.08
     Afgh
    -3.07
     Azerb
    -2.89
    anski
    -2.87
    phy
    -2.83
    ��
    -2.80
     Rudd
    -2.80
    POSITIVE LOGITS
     ES
    9.40
    ES
    5.61
     es
    5.58
    Es
    4.41
     ESL
    4.32
     EB
    4.25
     Es
    4.13
     EC
    4.10
     Esports
    3.68
     VMware
    3.68
    Activations Density 0.005%

    No Known Activations