© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 22283
    Prev
    Next
    INDEX
    Explanations

    references to the NFL Draft and its associated statistics or outcomes

    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
    0:0.20
    1:0.01
    2:0.37
    3:0.07
    4:0.02
    5:0.07
    6:0.02
    7:0.04
    8:0.06
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
     reconnect
    -3.22
     kW
    -2.85
     refuel
    -2.81
    Relations
    -2.74
     reconc
    -2.69
     repairs
    -2.64
    quit
    -2.63
    Battery
    -2.63
     restored
    -2.62
     repair
    -2.58
    POSITIVE LOGITS
    Draft
    5.30
     Draft
    5.12
     draft
    5.11
     drafted
    4.57
     drafts
    4.49
     drafting
    4.42
     selections
    4.30
     picks
    4.26
     scouts
    4.17
    draft
    4.15
    Activations Density 0.236%

    No Known Activations