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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43270
    Prev
    Next
    INDEX
    Explanations

    specific player names or identifiers in gaming contexts

    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
    2:0.10
    3:0.12
    4:0.05
    5:0.04
    6:0.34
    7:0.02
    8:0.06
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
    cture
    -1.31
     canal
    -1.31
     Reconstruction
    -1.22
     parcel
    -1.19
     fraught
    -1.16
    ournals
    -1.12
     APP
    -1.12
    pection
    -1.12
     device
    -1.11
     implant
    -1.11
    POSITIVE LOGITS
    ohan
    1.56
    ラン
    1.48
    �士
    1.39
    bass
    1.36
    llor
    1.36
    �
    1.34
    ilo
    1.33
    aiden
    1.31
    anton
    1.30
    Hash
    1.29
    Activations Density 0.004%

    No Known Activations