© 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. 19755
    Prev
    Next
    INDEX
    Explanations

    references to special attributes or characteristics that denote uniqueness or distinctiveness

    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
    1:0.38
    2:0.06
    3:0.07
    4:0.04
    5:0.04
    6:0.06
    7:0.04
    8:0.03
    9:0.08
    10:0.05
    11:0.03
    Negative Logits
    oday
    -3.30
     48
    -2.80
    zai
    -2.73
     97
    -2.69
     unequivocally
    -2.64
    oyle
    -2.63
    ‎
    -2.60
     98
    -2.60
     accurately
    -2.58
     67
    -2.57
    POSITIVE LOGITS
     kind
    7.21
     sort
    6.68
     kinds
    5.58
     kinda
    5.13
    kind
    5.07
     sorts
    5.03
     Kind
    4.67
    Kind
    4.21
    sort
    4.14
     type
    3.82
    Activations Density 0.015%

    No Known Activations