© 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. 10-ATT-KK
    11. 8656
    Prev
    Next
    INDEX
    Explanations

    words related to sports careers and player transitions

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.07
    4:0.05
    5:0.32
    6:0.03
    7:0.04
    8:0.01
    9:0.29
    10:0.01
    11:0.05
    Negative Logits
    mostly
    -2.55
     tended
    -2.48
    They
    -2.39
    ��
    -2.38
    opus
    -2.25
     pretended
    -2.25
    their
    -2.23
     ranged
    -2.21
    orted
    -2.15
    iuses
    -2.14
    POSITIVE LOGITS
     himself
    3.95
     tomorrow
    3.75
    morrow
    3.68
     his
    3.67
     someday
    3.58
     sooner
    3.32
     anytime
    3.17
     he
    3.16
     anyway
    3.15
     next
    3.11
    Activations Density 0.738%

    No Known Activations