© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20740
    Prev
    Next
    INDEX
    Explanations

    words that signify significant entities or actions related to accountability and transparency

    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
    0:0.24
    1:0.02
    2:0.20
    3:0.08
    4:0.04
    5:0.07
    6:0.05
    7:0.05
    8:0.06
    9:0.08
    10:0.04
    11:0.03
    Negative Logits
     gobl
    -3.01
    contract
    -3.00
    lore
    -2.87
    estead
    -2.83
    deals
    -2.79
    ggies
    -2.74
     lease
    -2.69
    ufact
    -2.65
    Contract
    -2.64
    Entity
    -2.59
    POSITIVE LOGITS
     screening
    7.49
     screenings
    7.09
     screened
    6.08
     Screen
    5.21
    Screen
    4.70
    screen
    4.12
     screen
    3.96
     screens
    3.90
     scanners
    3.71
     vetting
    3.49
    Activations Density 0.001%

    No Known Activations