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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11940
    Prev
    Next
    INDEX
    Explanations

    details related to performance attributes in athletes

    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
    0:0.07
    1:0.02
    2:0.05
    3:0.03
    4:0.04
    5:0.04
    6:0.25
    7:0.04
    8:0.07
    9:0.30
    10:0.01
    11:0.03
    Negative Logits
     Carpenter
    -3.90
    Hay
    -3.81
    outube
    -3.79
     ACS
    -3.78
     Gears
    -3.60
     Hobby
    -3.59
     sands
    -3.59
    Gear
    -3.55
     welf
    -3.49
     sand
    -3.45
    POSITIVE LOGITS
     Lu
    10.44
    Lu
    9.74
     LU
    6.72
    LU
    6.32
    lu
    6.22
     Lucy
    5.57
     Luis
    5.22
     Luigi
    4.64
    Luc
    4.39
     Luc
    4.38
    Activations Density 0.009%

    No Known Activations