© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14397
    Prev
    Next
    INDEX
    Explanations

    evaluative and comparative terms related to media quality

    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
    0:0.17
    1:0.04
    2:0.06
    3:0.06
    4:0.04
    5:0.02
    6:0.16
    7:0.21
    8:0.01
    9:0.03
    10:0.04
    11:0.11
    Negative Logits
     Hayward
    -2.55
     Coliseum
    -2.27
    displayText
    -2.26
     Cousins
    -2.18
     Detected
    -2.10
     bowl
    -2.07
     LF
    -2.05
     orche
    -2.01
     conductor
    -1.97
    ertodd
    -1.96
    POSITIVE LOGITS
     magazines
    4.13
     magazine
    4.09
    Magazine
    4.04
     Magazine
    3.23
     Playboy
    3.03
     publication
    3.02
     publishers
    3.00
     publications
    2.99
    azine
    2.93
     subscriptions
    2.77
    Activations Density 0.044%

    No Known Activations