© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44117
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.05
    3:0.04
    4:0.07
    5:0.03
    6:0.39
    7:0.09
    8:0.02
    9:0.03
    10:0.10
    11:0.08
    Negative Logits
    etsk
    -1.30
     omission
    -1.27
     hus
    -1.26
     inherent
    -1.19
    usive
    -1.19
     Fargo
    -1.16
    assetsadobe
    -1.15
    Jones
    -1.11
    lycer
    -1.11
     chore
    -1.10
    POSITIVE LOGITS
    lished
    1.45
    thur
    1.41
    ntil
    1.38
    ��
    1.34
    merce
    1.34
     Telescope
    1.31
    States
    1.31
    ainer
    1.29
    aroo
    1.26
     Regions
    1.25
    Activations Density 0.003%

    No Known Activations