© 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. 786
    Prev
    Next
    INDEX
    Explanations

    references to internet standards and specifications

    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
    0:0.21
    1:0.02
    2:0.17
    3:0.09
    4:0.04
    5:0.10
    6:0.04
    7:0.05
    8:0.09
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
    assic
    -2.56
    essional
    -2.56
     guilt
    -2.54
     Gamble
    -2.52
     remorse
    -2.43
     Fathers
    -2.42
     Palin
    -2.40
    Jew
    -2.38
    Batman
    -2.37
     pray
    -2.32
    POSITIVE LOGITS
     IEEE
    5.44
     interoper
    4.48
    RFC
    4.27
     Ethernet
    4.23
     RFC
    4.20
     protocols
    3.96
     802
    3.92
     implementations
    3.86
     protocol
    3.84
     specification
    3.82
    Activations Density 0.016%

    No Known Activations