© 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. 21109
    Prev
    Next
    INDEX
    Explanations

    references to concepts of belonging or possession

    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
    0:0.08
    1:0.07
    2:0.09
    3:0.07
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.10
    11:0.07
    Negative Logits
     bio
    -2.56
     "@
    -2.55
     physic
    -2.46
    oxy
    -2.44
    oa
    -2.39
    feed
    -2.38
     electron
    -2.38
    ato
    -2.33
    DonaldTrump
    -2.31
     digitally
    -2.27
    POSITIVE LOGITS
    �
    3.34
    quickShipAvailable
    2.89
    quished
    2.82
    olitan
    2.71
    furt
    2.67
     Sind
    2.59
     Flavoring
    2.59
    inav
    2.58
    ウス
    2.57
    ヴァ
    2.49
    Activations Density 0.000%

    No Known Activations