© 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. 10-ATT-KK
    11. 13959
    Prev
    Next
    INDEX
    Explanations

    questions and discussions surrounding relationships and personal experiences across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.04
    2:0.16
    3:0.13
    4:0.12
    5:0.08
    6:0.02
    7:0.05
    8:0.04
    9:0.08
    10:0.04
    11:0.05
    Negative Logits
     Newark
    -2.84
     JFK
    -2.79
     Krug
    -2.70
    oston
    -2.69
     Delta
    -2.59
     502
    -2.54
    velt
    -2.49
     Hayward
    -2.48
    ardy
    -2.46
     FDR
    -2.46
    POSITIVE LOGITS
    �
    5.33
     ●
    4.43
     �
    4.39
     │
    4.17
    ●
    3.94
     �
    3.90
     ‎
    3.81
    �
    3.70
        
    3.63
     �
    3.44
    Activations Density 0.070%

    No Known Activations