© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8479
    Prev
    Next
    INDEX
    Explanations

    words related to customization and personal adaptation

    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
    1:0.13
    2:0.08
    3:0.05
    4:0.03
    5:0.06
    6:0.23
    7:0.03
    8:0.02
    9:0.20
    10:0.03
    11:0.02
    Negative Logits
    rail
    -4.08
     Bah
    -3.90
     Leh
    -3.62
     Railroad
    -3.40
     Burgess
    -3.20
     Bore
    -3.17
    Rail
    -3.16
     Stall
    -3.15
     Bend
    -3.13
     Bus
    -3.08
    POSITIVE LOGITS
     Custom
    6.56
    Custom
    6.14
     custom
    5.54
     customization
    5.47
    custom
    5.45
     customize
    5.41
     customized
    5.39
     personalized
    4.66
     customizable
    4.61
    ustom
    4.50
    Activations Density 0.001%

    No Known Activations