© 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. 20086
    Prev
    Next
    INDEX
    Explanations

    formal or structured language indicative of definitions or explanations

    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
    0:0.05
    1:0.01
    2:0.04
    3:0.03
    4:0.05
    5:0.03
    6:0.39
    7:0.04
    8:0.07
    9:0.19
    10:0.03
    11:0.03
    Negative Logits
    sbm
    -3.92
    minecraft
    -3.55
     linen
    -3.46
    idi
    -3.39
     ELE
    -3.28
     Heidi
    -3.23
     textile
    -3.23
    liners
    -3.22
     intrins
    -3.21
     Twisted
    -3.21
    POSITIVE LOGITS
     Bay
    10.37
    Bay
    10.07
     bay
    9.66
    bay
    8.21
     Beach
    4.75
     Harbour
    4.46
     Harbor
    4.42
     Hayward
    4.34
     Sea
    4.24
    Cap
    4.23
    Activations Density 0.015%

    No Known Activations