© 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. 11103
    Prev
    Next
    INDEX
    Explanations

    references to organized crime dynamics and influential figures within it

    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
    0:0.16
    1:0.01
    2:0.23
    3:0.09
    4:0.03
    5:0.09
    6:0.05
    7:0.07
    8:0.14
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
     ultrasound
    -2.86
    perature
    -2.81
     Atmospheric
    -2.77
    oscopic
    -2.69
     Astron
    -2.66
    NASA
    -2.60
     Telescope
    -2.60
    Widget
    -2.58
     Temperature
    -2.56
    Reviewed
    -2.55
    POSITIVE LOGITS
     gang
    5.72
     gangs
    5.69
    gang
    5.00
     Mafia
    4.69
     cartel
    4.53
     mafia
    4.47
     extortion
    4.38
     vigilante
    4.26
     Gang
    4.16
     homicides
    3.95
    Activations Density 0.172%

    No Known Activations