© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3172
    Prev
    Next
    INDEX
    Explanations

    instances of intimidation and manipulation in various contexts

    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
    1:0.02
    2:0.05
    3:0.06
    4:0.13
    5:0.03
    6:0.04
    7:0.36
    8:0.03
    9:0.03
    10:0.09
    11:0.09
    Negative Logits
    variable
    -1.45
    rh
    -1.35
     Somewhere
    -1.31
    fixed
    -1.31
     salvage
    -1.28
    album
    -1.27
    amy
    -1.27
     Imaging
    -1.27
    ゴン
    -1.23
     miracle
    -1.21
    POSITIVE LOGITS
     opponents
    1.72
     foes
    1.70
     passers
    1.65
     subordinates
    1.64
     intimidated
    1.58
     challengers
    1.57
     adversaries
    1.54
     superiors
    1.53
     bullies
    1.48
     merciless
    1.43
    Activations Density 0.003%

    No Known Activations