© 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. 18447
    Prev
    Next
    INDEX
    Explanations

    information related to corporate announcements and activities

    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
    0:0.12
    1:0.03
    2:0.11
    3:0.10
    4:0.06
    5:0.10
    6:0.07
    7:0.08
    8:0.11
    9:0.07
    10:0.06
    11:0.04
    Negative Logits
     Kramer
    -2.77
    �
    -2.67
     torped
    -2.61
     Bucs
    -2.57
    overty
    -2.56
     loneliness
    -2.56
     Romantic
    -2.50
     torpedo
    -2.48
     cursing
    -2.46
    enegger
    -2.44
    POSITIVE LOGITS
    Canadian
    3.60
     Canadian
    3.51
     Ottawa
    3.42
     Canada
    3.23
    Canada
    3.21
     Cannabis
    3.18
     authorised
    3.14
     cannabis
    3.08
     THC
    3.02
     Pharm
    3.01
    Activations Density 0.003%

    No Known Activations