© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 18933
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their roles or actions related to corporate or investigative contexts

    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
    0:0.07
    1:0.03
    2:0.06
    3:0.03
    4:0.05
    5:0.05
    6:0.22
    7:0.06
    8:0.07
    9:0.26
    10:0.02
    11:0.05
    Negative Logits
     condom
    -3.86
     latex
    -3.79
     Cond
    -3.75
     prom
    -3.68
     vertex
    -3.66
     flu
    -3.66
     Perse
    -3.65
     dam
    -3.50
     horm
    -3.49
     Flu
    -3.47
    POSITIVE LOGITS
     Andy
    9.23
    Andy
    9.13
    Andrew
    4.81
     Andrew
    4.64
     Andrews
    4.25
     Timbers
    4.20
     Allen
    4.17
    Allen
    3.97
    Lewis
    3.85
     Ore
    3.82
    Activations Density 0.003%

    No Known Activations