© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20356
    Prev
    Next
    INDEX
    Explanations

    concepts related to cable and satellite television services and consumer complaints regarding them

    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
    0:0.12
    1:0.03
    2:0.03
    3:0.04
    4:0.07
    5:0.02
    6:0.03
    7:0.42
    8:0.02
    9:0.03
    10:0.03
    11:0.11
    Negative Logits
     Cater
    -3.47
     Carn
    -2.86
    cor
    -2.86
     Carbon
    -2.79
     Cable
    -2.77
     McLaren
    -2.75
     Carrier
    -2.65
     Libre
    -2.62
     Ether
    -2.62
     CAR
    -2.61
    POSITIVE LOGITS
    zai
    3.07
    Sav
    2.58
    olson
    2.45
    alf
    2.38
    rowth
    2.37
     Richards
    2.37
     shin
    2.33
     Mighty
    2.32
    apeake
    2.32
    EGA
    2.31
    Activations Density 0.010%

    No Known Activations