© 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. 9008
    Prev
    Next
    INDEX
    Explanations

    phrases related to electric power systems and their applications

    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
    0:0.13
    1:0.03
    2:0.13
    3:0.05
    4:0.05
    5:0.05
    6:0.12
    7:0.07
    8:0.10
    9:0.17
    10:0.02
    11:0.03
    Negative Logits
     clans
    -3.91
     McCann
    -3.81
     Somalia
    -3.58
     Chains
    -3.56
     clan
    -3.40
     GSL
    -3.40
     cov
    -3.33
    McC
    -3.30
    Dat
    -3.27
     checkpoints
    -3.24
    POSITIVE LOGITS
     Edison
    10.45
     Nikola
    5.06
     Tesla
    4.60
     Einstein
    4.60
     Electro
    4.41
    Tesla
    4.19
     inventor
    4.17
     Newton
    4.00
     Tinker
    3.94
     electric
    3.90
    Activations Density 0.001%

    No Known Activations