Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 394
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals involved in criminal activities or legal issues

    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
    0:0.08
    1:0.02
    2:0.05
    3:0.02
    4:0.06
    5:0.04
    6:0.25
    7:0.05
    8:0.08
    9:0.24
    10:0.02
    11:0.02
    Negative Logits
     Gears
    -4.21
     pit
    -4.03
     Chimera
    -4.01
    SPA
    -3.69
    Bridge
    -3.68
     Xan
    -3.61
     Viper
    -3.53
    hur
    -3.50
    xit
    -3.45
     benz
    -3.45
    POSITIVE LOGITS
     Fred
    10.06
    Fred
    9.92
     Frederick
    6.47
    fred
    6.37
     Freddy
    6.16
     Freder
    5.84
     Freddie
    5.80
     Fried
    5.13
     Howard
    4.45
     Clyde
    4.33
    Activations Density 0.013%

    No Known Activations