© 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. 10499
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their actions in relation to legal or ethical 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
    0:0.15
    1:0.01
    2:0.21
    3:0.08
    4:0.02
    5:0.13
    6:0.03
    7:0.06
    8:0.16
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
    ipeg
    -3.41
     Winnipeg
    -2.89
    nz
    -2.89
    ombies
    -2.88
     Zi
    -2.73
    obyl
    -2.73
    ombie
    -2.67
    NZ
    -2.65
     labou
    -2.60
    uckland
    -2.56
    POSITIVE LOGITS
     Sessions
    5.62
     DOJ
    4.25
     Rosenstein
    3.58
     Attorney
    3.55
     Alabama
    3.54
     attorney
    3.49
    Alabama
    3.42
     Session
    3.23
    Attorney
    3.19
    orneys
    3.14
    Activations Density 0.034%

    No Known Activations