© 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. 9-ATT-KK
    11. 20061
    Prev
    Next
    INDEX
    Explanations

    conjunctions and prepositions that indicate relationships or connections between ideas

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.08
    4:0.03
    5:0.05
    6:0.04
    7:0.50
    8:0.04
    9:0.03
    10:0.04
    11:0.02
    Negative Logits
    fed
    -2.82
    Bang
    -2.67
    Naz
    -2.31
     IMAGES
    -2.21
    amaru
    -2.21
    atoon
    -2.21
    asia
    -2.17
    �
    -2.17
    �
    -2.17
    jab
    -2.16
    POSITIVE LOGITS
     private
    4.76
    private
    4.00
    Private
    3.92
     Private
    3.81
     privately
    3.40
     confidential
    2.89
     proprietary
    2.79
    compan
    2.69
     obscure
    2.59
     secretive
    2.58
    Activations Density 0.051%

    No Known Activations