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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 11383
    Prev
    Next
    INDEX
    Explanations

    terms related to sports and competitive events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.07
    2:0.24
    3:0.04
    4:0.02
    5:0.03
    6:0.13
    7:0.09
    8:0.10
    9:0.05
    10:0.07
    11:0.08
    Negative Logits
    cipled
    -1.24
    iversal
    -1.10
     Pradesh
    -1.09
    english
    -1.07
     embodiments
    -1.06
    龍喚士
    -1.05
     behavi
    -1.03
    ��
    -1.03
     linem
    -1.02
     advoc
    -0.99
    POSITIVE LOGITS
    osphere
    1.48
     moniker
    1.40
    liest
    1.36
     logo
    1.35
     cra
    1.34
    iest
    1.31
    hest
    1.27
     playbook
    1.21
     bandwagon
    1.19
    elight
    1.17
    Activations Density 0.930%

    No Known Activations