© 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. 18791
    Prev
    Next
    INDEX
    Explanations

    references to the Quran or Quranic concepts

    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
    2:0.09
    3:0.07
    4:0.07
    5:0.07
    6:0.10
    7:0.09
    8:0.08
    9:0.08
    10:0.07
    11:0.09
    Negative Logits
     Nut
    -2.65
     Anita
    -2.64
     inserts
    -2.58
     Potter
    -2.54
     tot
    -2.42
     Dunham
    -2.41
     advertisements
    -2.40
     pornography
    -2.40
     Judd
    -2.39
     Hearth
    -2.39
    POSITIVE LOGITS
    ouver
    3.12
    selage
    3.04
    ugal
    2.95
    enezuel
    2.95
    Boss
    2.92
     hurricanes
    2.92
    etheus
    2.91
    usc
    2.89
    ascus
    2.88
    --+
    2.86
    Activations Density 0.000%

    No Known Activations