© 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. 18497
    Prev
    Next
    INDEX
    Explanations

    prominent or repetitive references to subjects or entities in a text

    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
    0:0.06
    1:0.24
    2:0.06
    3:0.10
    4:0.05
    5:0.06
    6:0.06
    7:0.07
    8:0.05
    9:0.07
    10:0.08
    11:0.05
    Negative Logits
     compared
    -2.59
     including
    -2.50
     moder
    -2.33
     hard
    -2.33
     spaced
    -2.30
     stressed
    -2.26
     though
    -2.26
     analysed
    -2.19
     differed
    -2.18
     ranged
    -2.11
    POSITIVE LOGITS
    ウス
    3.19
    20439
    3.06
    ntil
    2.97
    }}}
    2.80
    pload
    2.77
    ailability
    2.76
    ��
    2.75
    llah
    2.73
    ディ
    2.64
    ply
    2.63
    Activations Density 0.000%

    No Known Activations