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. 9-ATT-KK
    6. 11288
    Prev
    Next
    INDEX
    Explanations

    references to former leaders and political alliances

    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
    1:0.03
    2:0.07
    3:0.04
    4:0.06
    5:0.04
    6:0.18
    7:0.05
    8:0.08
    9:0.27
    10:0.03
    11:0.04
    Negative Logits
     Wu
    -3.20
     Poe
    -3.19
    oe
    -3.16
     Lowell
    -3.15
     pri
    -3.10
    ierce
    -3.08
    legram
    -3.06
     Rowe
    -3.05
    к
    -3.02
     Eleanor
    -2.95
    POSITIVE LOGITS
     Iraqis
    8.09
     Baghdad
    7.48
    Iraq
    7.45
     Iraq
    7.41
     Saddam
    7.28
     Iraqi
    7.23
     Hussein
    6.23
     Bush
    4.29
     Bowen
    4.07
     Mosul
    4.05
    Activations Density 0.007%

    No Known Activations