© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    specific numerical scores or ratings related to gaming performance

    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
    0:0.03
    1:0.01
    2:0.12
    3:0.05
    4:0.05
    5:0.03
    6:0.16
    7:0.12
    8:0.10
    9:0.05
    10:0.18
    11:0.04
    Negative Logits
     Cheong
    -1.62
     undisclosed
    -1.55
    ディ
    -1.55
    anu
    -1.54
     Kau
    -1.49
     サーティワン
    -1.45
    angelo
    -1.44
    カ
    -1.44
    hement
    -1.42
     ISI
    -1.42
    POSITIVE LOGITS
    PASS
    1.90
     matchups
    1.79
    kill
    1.70
    against
    1.66
    essions
    1.62
     finals
    1.60
     Blitz
    1.56
    fights
    1.55
    RAW
    1.55
     Showdown
    1.54
    Activations Density 0.000%

    No Known Activations