© 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. 10728
    Prev
    Next
    INDEX
    Explanations

    phrases that express falsehood or deception

    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
    1:0.08
    2:0.08
    3:0.07
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    estate
    -3.58
    essen
    -3.54
    Hispanic
    -2.94
    Southern
    -2.93
    gas
    -2.89
    aum
    -2.88
    atown
    -2.86
    roe
    -2.77
    overty
    -2.72
    tin
    -2.70
    POSITIVE LOGITS
     Typhoon
    2.81
     Typh
    2.60
     Shogun
    2.57
     Bus
    2.47
     Jinping
    2.45
     doubtless
    2.41
     queues
    2.39
     Constable
    2.38
     Farage
    2.36
     Huawei
    2.36
    Activations Density 0.000%

    No Known Activations