© 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. 10294
    Prev
    Next
    INDEX
    Explanations

    expressions of opinions or beliefs about societal issues

    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
    0:0.18
    1:0.01
    2:0.20
    3:0.06
    4:0.02
    5:0.09
    6:0.09
    7:0.04
    8:0.14
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
     FSA
    -3.90
     Nanto
    -3.52
    iku
    -3.46
    ushima
    -3.44
    yip
    -3.35
     Territories
    -3.27
    merga
    -3.13
     MSI
    -3.07
    akura
    -3.03
    iHUD
    -3.02
    POSITIVE LOGITS
     Cosby
    8.21
    Cos
    4.92
     comedian
    4.39
     Oprah
    4.03
     Comedy
    4.00
     comedians
    3.88
     Comed
    3.80
     Colbert
    3.79
     onstage
    3.44
     Pryor
    3.39
    Activations Density 0.001%

    No Known Activations