© 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. 5-ATT-KK
    6. 35989
    Prev
    Next
    INDEX
    Explanations

    references to people in leadership or influential positions within various organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.07
    3:0.06
    4:0.04
    5:0.03
    6:0.02
    7:0.03
    8:0.03
    9:0.06
    10:0.47
    11:0.11
    Negative Logits
     colonies
    -1.57
    soc
    -1.55
     lows
    -1.51
    Revolution
    -1.49
    itars
    -1.45
     Classical
    -1.45
     rappers
    -1.44
     dens
    -1.43
     decriminal
    -1.43
     legalization
    -1.41
    POSITIVE LOGITS
     overseeing
    2.59
     superv
    2.20
     oversee
    2.17
     oversees
    2.00
    BuyableInstoreAndOnline
    1.96
     oversaw
    1.96
     subordinates
    1.96
    office
    1.94
     tasked
    1.84
     advising
    1.81
    Activations Density 1.057%

    No Known Activations