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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 64
    Prev
    Next
    INDEX
    Explanations

    details related to space exploration and celestial bodies

    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
    0:0.17
    1:0.03
    2:0.10
    3:0.06
    4:0.04
    5:0.07
    6:0.06
    7:0.06
    8:0.22
    9:0.07
    10:0.03
    11:0.03
    Negative Logits
     Wong
    -3.49
     Karachi
    -3.42
    Hong
    -3.36
     CAD
    -3.25
     Keane
    -3.23
    efe
    -3.19
     Malik
    -3.15
     Prairie
    -3.14
    atown
    -3.09
     McKin
    -3.06
    POSITIVE LOGITS
     Saturn
    7.44
     moons
    5.00
     Titan
    4.72
     Uran
    4.45
     Titans
    4.22
     Jupiter
    4.21
     Cass
    4.16
     orbits
    4.01
    Cass
    3.85
     Pluto
    3.83
    Activations Density 0.007%

    No Known Activations