© 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. 346
    Prev
    Next
    INDEX
    Explanations

    terms related to organization or sorting processes

    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
    0:0.16
    1:0.08
    2:0.14
    3:0.04
    4:0.05
    5:0.04
    6:0.12
    7:0.05
    8:0.04
    9:0.14
    10:0.03
    11:0.06
    Negative Logits
    kee
    -3.23
     McF
    -3.20
     Cock
    -3.17
    KC
    -3.17
    KEN
    -3.13
     Pav
    -3.13
     Kaw
    -3.11
    CE
    -3.11
     Grip
    -3.04
     Killer
    -2.96
    POSITIVE LOGITS
     sorting
    6.84
     sorted
    6.29
    Sort
    5.75
     Sort
    5.61
    sort
    5.49
    orted
    4.22
    phabet
    4.04
    reverse
    3.84
    orting
    3.75
     sort
    3.65
    Activations Density 0.003%

    No Known Activations