Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11408
    Prev
    Next
    INDEX
    Explanations

    phrases related to unions and collective representation of workers

    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
    0:0.07
    1:0.01
    2:0.13
    3:0.13
    4:0.03
    5:0.36
    6:0.03
    7:0.05
    8:0.06
    9:0.03
    10:0.03
    11:0.01
    Negative Logits
     organisation
    -2.33
     organis
    -2.27
    organ
    -2.23
     org
    -2.18
    �
    -2.16
    Organ
    -2.11
    spirit
    -2.04
     サーティワン
    -2.02
    iliated
    -1.95
     mastermind
    -1.93
    POSITIVE LOGITS
    cuts
    2.19
     Mandatory
    2.12
     reversible
    2.07
     policymakers
    1.93
     Ending
    1.90
     removal
    1.89
     motorists
    1.88
     unwanted
    1.86
     improper
    1.84
     harsher
    1.84
    Activations Density 0.733%

    No Known Activations