© 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. 18826
    Prev
    Next
    INDEX
    Explanations

    references to facts and evidence in discussions or arguments

    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
    0:0.06
    1:0.24
    2:0.06
    3:0.06
    4:0.04
    5:0.05
    6:0.14
    7:0.05
    8:0.03
    9:0.17
    10:0.03
    11:0.02
    Negative Logits
     Lank
    -3.21
    iliary
    -3.15
     Liang
    -3.13
     Laksh
    -2.86
    interstitial
    -2.84
     Salman
    -2.74
    eny
    -2.73
     Kyoto
    -2.71
     Kare
    -2.70
    Pad
    -2.65
    POSITIVE LOGITS
     Fact
    6.17
    fact
    5.79
    Fact
    5.49
     fact
    5.10
     facts
    4.92
    facts
    4.91
     Facts
    4.37
     factual
    4.07
     falsehood
    3.69
     FAC
    3.65
    Activations Density 0.007%

    No Known Activations