© 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. 41246
    Prev
    Next
    INDEX
    Explanations

    instances of actions followed by their agents, particularly in contexts involving violence or conflict

    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
    0:0.01
    1:0.01
    2:0.11
    3:0.05
    4:0.14
    5:0.02
    6:0.03
    7:0.20
    8:0.03
    9:0.03
    10:0.18
    11:0.13
    Negative Logits
     subscriptions
    -1.60
    DragonMagazine
    -1.51
     inbox
    -1.50
     finances
    -1.46
     organise
    -1.44
     calendars
    -1.41
    ipolar
    -1.40
    cation
    -1.37
    orders
    -1.33
     subscription
    -1.31
    POSITIVE LOGITS
     Peck
    1.57
     Sergeant
    1.55
     Hail
    1.50
     Feinstein
    1.48
     Thur
    1.42
     Barth
    1.42
     Fas
    1.41
    anie
    1.41
     Stab
    1.41
     Alive
    1.41
    Activations Density 0.003%

    No Known Activations