© 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. 8992
    Prev
    Next
    INDEX
    Explanations

    references to prominent television hosts and their shows

    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
    0:0.34
    1:0.04
    2:0.04
    3:0.08
    4:0.07
    5:0.03
    6:0.08
    7:0.07
    8:0.03
    9:0.06
    10:0.05
    11:0.06
    Negative Logits
     Typhoon
    -5.00
    �
    -4.20
     Zen
    -4.03
     Panzer
    -3.84
     helicopter
    -3.84
    �
    -3.76
     mindfulness
    -3.75
     Anaheim
    -3.64
     Helic
    -3.61
     Ana
    -3.58
    POSITIVE LOGITS
     Pryor
    4.15
    ````
    4.11
     mt
    3.91
    mt
    3.75
     Clarks
    3.58
     Weir
    3.50
     Bryant
    3.37
     Bris
    3.32
     Barcl
    3.31
    Las
    3.21
    Activations Density 0.001%

    No Known Activations