© 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. 21365
    Prev
    Next
    INDEX
    Explanations

    references to social media engagement and connections

    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
    0:0.15
    1:0.05
    2:0.09
    3:0.17
    4:0.06
    5:0.08
    6:0.05
    7:0.08
    8:0.07
    9:0.03
    10:0.08
    11:0.03
    Negative Logits
     tasting
    -2.67
     beer
    -2.51
     acoustic
    -2.40
     hatch
    -2.40
     lingu
    -2.39
     cavern
    -2.39
     suitcase
    -2.39
     cartridge
    -2.39
     crammed
    -2.38
     whisky
    -2.37
    POSITIVE LOGITS
     Follow
    3.38
     Blocks
    3.09
     Updates
    3.08
     Notification
    3.08
     Shares
    3.06
     Posts
    3.04
     retweet
    3.02
    Block
    3.01
     Activity
    2.96
     Tweet
    2.95
    Activations Density 0.010%

    No Known Activations