Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7655
    Prev
    Next
    INDEX
    Explanations

    references to individuals associated with political contexts, particularly those related to the Khan family and significant figures in current affairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.04
    2:0.10
    3:0.14
    4:0.02
    5:0.03
    6:0.15
    7:0.17
    8:0.06
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
     Spartans
    -1.01
     Scrib
    -1.01
    pection
    -0.96
     Eucl
    -0.95
     cent
    -0.92
     monog
    -0.90
     mammals
    -0.89
     Sensor
    -0.89
     Sloan
    -0.89
     tumble
    -0.88
    POSITIVE LOGITS
    isma
    1.30
    allah
    1.28
    oglu
    1.26
    enei
    1.20
    iru
    1.17
    nai
    1.16
    angan
    1.16
    aba
    1.16
    Allah
    1.15
    arat
    1.15
    Activations Density 0.009%

    No Known Activations