© 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. 2981
    Prev
    Next
    INDEX
    Explanations

    references to server architecture and configurations

    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
    0:0.09
    1:0.06
    2:0.06
    3:0.03
    4:0.04
    5:0.03
    6:0.26
    7:0.04
    8:0.04
    9:0.25
    10:0.01
    11:0.03
    Negative Logits
     Herrera
    -4.26
     taxis
    -4.00
     taxi
    -3.99
     Rabb
    -3.75
     Polo
    -3.53
     Taxi
    -3.53
     Uruguay
    -3.50
    oufl
    -3.42
     rain
    -3.40
     Urug
    -3.38
    POSITIVE LOGITS
     Core
    8.71
    Core
    8.06
     cores
    6.85
    core
    6.69
     core
    6.52
     Corey
    4.69
     CNS
    4.46
     Kore
    4.33
     CP
    4.07
    ORE
    3.92
    Activations Density 0.010%

    No Known Activations