© 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. 10199
    Prev
    Next
    INDEX
    Explanations

    references to Apple and its CEO, Tim Cook, in relation to corporate actions and responsibilities

    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
    0:0.37
    1:0.01
    2:0.11
    3:0.08
    4:0.02
    5:0.06
    6:0.02
    7:0.05
    8:0.17
    9:0.02
    10:0.02
    11:0.01
    Negative Logits
     Byrd
    -3.05
     Buchanan
    -2.89
     Phelps
    -2.80
     Worcester
    -2.78
    ersen
    -2.75
     Leone
    -2.67
     rugby
    -2.66
    henko
    -2.66
     NH
    -2.64
     referee
    -2.62
    POSITIVE LOGITS
     Apple
    5.77
    Apple
    5.59
     iCloud
    5.24
     Macintosh
    5.17
     iPhones
    4.98
     iPhone
    4.93
     iOS
    4.77
     MacBook
    4.42
    iPhone
    4.30
     iPod
    4.30
    Activations Density 0.103%

    No Known Activations