© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3609
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory issues related to a specific term or concept

    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
    0:0.10
    1:0.05
    2:0.10
    3:0.05
    4:0.06
    5:0.04
    6:0.17
    7:0.05
    8:0.04
    9:0.21
    10:0.03
    11:0.05
    Negative Logits
     Lomb
    -3.45
     Kidd
    -3.31
     Bulg
    -3.27
     Gunn
    -3.26
     Mongol
    -3.25
     Haj
    -3.24
    aults
    -3.23
     Mongolia
    -3.15
     Benn
    -3.14
     Charg
    -3.07
    POSITIVE LOGITS
     synthetic
    8.26
     Synt
    6.91
     synt
    6.49
     Artificial
    4.58
    hetic
    4.29
    hetics
    4.26
     artificial
    4.22
     nylon
    4.22
     synthes
    4.21
     synth
    4.20
    Activations Density 0.001%

    No Known Activations