© 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. 8677
    Prev
    Next
    INDEX
    Explanations

    references to various types of media content and their contexts

    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
    0:0.07
    1:0.04
    2:0.06
    3:0.05
    4:0.06
    5:0.05
    6:0.15
    7:0.04
    8:0.09
    9:0.27
    10:0.03
    11:0.07
    Negative Logits
     Coral
    -4.25
     Bran
    -4.10
     Clemson
    -3.88
     Roses
    -3.87
     Cosmos
    -3.59
     Sail
    -3.59
     Bacon
    -3.50
    Closure
    -3.42
     Bod
    -3.42
     Rivers
    -3.37
    POSITIVE LOGITS
     MP
    9.56
    MP
    8.10
    MK
    6.58
     MK
    6.37
    mp
    6.33
     mp
    6.17
     MPs
    5.96
    Mp
    5.36
     MEP
    4.92
     Meg
    4.44
    Activations Density 0.002%

    No Known Activations