© 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. 35595
    Prev
    Next
    INDEX
    Explanations

    mentions of players, staff, and their interactions within a team context

    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
    0:0.04
    1:0.02
    2:0.09
    3:0.04
    4:0.06
    5:0.03
    6:0.38
    7:0.04
    8:0.04
    9:0.04
    10:0.10
    11:0.08
    Negative Logits
    OTH
    -1.25
    龍契士
    -1.22
    URR
    -1.22
    Js
    -1.20
     Crescent
    -1.19
     Typhoon
    -1.18
    igmat
    -1.13
     Whale
    -1.12
    utsche
    -1.11
     lil
    -1.10
    POSITIVE LOGITS
    EStream
    1.48
    ichick
    1.41
    establishment
    1.37
    KNOWN
    1.33
     Constantin
    1.31
    imity
    1.29
    render
    1.29
    ilipp
    1.28
    elected
    1.26
    oyal
    1.24
    Activations Density 0.011%

    No Known Activations