© 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. 10-ATT-KK
    11. 14427
    Prev
    Next
    INDEX
    Explanations

    phrases associated with the concept of camels and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.26
    1:0.05
    2:0.05
    3:0.06
    4:0.04
    5:0.03
    6:0.07
    7:0.06
    8:0.03
    9:0.04
    10:0.20
    11:0.05
    Negative Logits
     ICE
    -3.84
     Sergei
    -3.71
     SPI
    -3.63
    я
    -3.52
    Pi
    -3.39
     Pier
    -3.35
    Sch
    -3.29
     Helsinki
    -3.26
    EngineDebug
    -3.24
     Kus
    -3.23
    POSITIVE LOGITS
     camel
    10.38
     Camel
    10.22
     cam
    5.78
    amel
    4.91
     Cam
    4.73
     caravan
    4.59
     Jordanian
    4.46
     Jordan
    4.33
    cam
    4.26
     Arabian
    4.18
    Activations Density 0.002%

    No Known Activations