© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    references to specific characters and relationships within narratives

    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
    0:0.11
    1:0.05
    2:0.07
    3:0.07
    4:0.06
    5:0.06
    6:0.06
    7:0.06
    8:0.22
    9:0.06
    10:0.07
    11:0.07
    Negative Logits
    utterstock
    -3.33
     Idlib
    -3.16
     Duc
    -3.11
    wine
    -2.90
     Pier
    -2.90
    ottesville
    -2.83
     Igor
    -2.81
    otine
    -2.79
     Mare
    -2.78
     Suffolk
    -2.73
    POSITIVE LOGITS
     Starg
    7.10
     SG
    5.26
    SG
    4.90
     Hyder
    3.75
     cricket
    3.71
     Cricket
    3.61
     Asgard
    3.38
     Klingon
    3.25
     Islamabad
    3.22
     Kling
    3.17
    Activations Density 0.001%

    No Known Activations