© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 21418
    Prev
    Next
    INDEX
    Explanations

    statements related to events or actions that involve injury or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.02
    2:0.08
    3:0.03
    4:0.07
    5:0.03
    6:0.25
    7:0.05
    8:0.09
    9:0.18
    10:0.02
    11:0.03
    Negative Logits
     Sakuya
    -4.59
     incorpor
    -3.84
    Ghost
    -3.82
     NAV
    -3.71
    ilan
    -3.70
     transformer
    -3.68
     nun
    -3.58
     CT
    -3.54
     convent
    -3.51
     Tunnel
    -3.42
    POSITIVE LOGITS
     Bryant
    12.26
     Kobe
    8.90
     Lakers
    7.11
     Kare
    5.68
     Bry
    5.59
     Durant
    5.43
     Chamberlain
    5.40
     Byr
    5.25
     Barkley
    5.25
     Lionel
    4.86
    Activations Density 0.008%

    No Known Activations