© 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. 10205
    Prev
    Next
    INDEX
    Explanations

    references to social media interactions and platforms

    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
    0:0.26
    1:0.01
    2:0.04
    3:0.12
    4:0.03
    5:0.16
    6:0.02
    7:0.08
    8:0.13
    9:0.02
    10:0.06
    11:0.02
    Negative Logits
     broch
    -2.25
    yip
    -2.11
     Nordic
    -2.04
     Farage
    -2.01
     Yamaha
    -2.00
     literature
    -1.96
    dfx
    -1.89
     annex
    -1.88
     Hague
    -1.88
     Norwegian
    -1.86
    POSITIVE LOGITS
    berto
    2.14
    abc
    2.08
    �
    1.93
     �
    1.89
    Ore
    1.87
    roach
    1.86
     DEFENSE
    1.85
    azo
    1.84
    Oregon
    1.84
    daily
    1.80
    Activations Density 0.017%

    No Known Activations