© 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. 37102
    Prev
    Next
    INDEX
    Explanations

    expression of sports team names and their players

    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
    0:0.08
    1:0.06
    2:0.09
    3:0.09
    4:0.04
    5:0.04
    6:0.07
    7:0.02
    8:0.09
    9:0.10
    10:0.13
    11:0.14
    Negative Logits
    apter
    -1.40
    acea
    -1.37
    aid
    -1.31
    osponsors
    -1.31
     DOT
    -1.25
    ularity
    -1.24
    ife
    -1.24
    rep
    -1.24
    ATA
    -1.23
    ousand
    -1.23
    POSITIVE LOGITS
     holiest
    1.48
    Conclusion
    1.33
    Iv
    1.32
    amins
    1.29
     Koran
    1.20
     Hussein
    1.20
    hett
    1.20
     mosques
    1.18
     Uzbek
    1.18
    EStream
    1.18
    Activations Density 0.002%

    No Known Activations