© 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. 3442
    Prev
    Next
    INDEX
    Explanations

    negations and references to Donald Trump or his campaign

    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
    0:0.05
    1:0.15
    2:0.06
    3:0.08
    4:0.05
    5:0.05
    6:0.07
    7:0.06
    8:0.03
    9:0.26
    10:0.06
    11:0.04
    Negative Logits
     proxies
    -3.00
    abit
    -2.90
     proxy
    -2.85
     Oman
    -2.53
    iday
    -2.50
    omething
    -2.50
     Piet
    -2.49
     pigeon
    -2.48
     Anon
    -2.47
     ISI
    -2.43
    POSITIVE LOGITS
    NVIDIA
    2.89
    RAG
    2.73
     Lu
    2.70
     Rapt
    2.67
     blush
    2.61
     Fir
    2.60
    rea
    2.58
    HR
    2.56
     NCT
    2.53
    HA
    2.53
    Activations Density 0.001%

    No Known Activations