© 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. 2-ATT-KK
    11. 21554
    Prev
    Next
    INDEX
    Explanations

    phrases related to the complexity and nuances of love, including its emotional impact and contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.05
    2:0.12
    3:0.09
    4:0.03
    5:0.09
    6:0.03
    7:0.04
    8:0.07
    9:0.25
    10:0.08
    11:0.04
    Negative Logits
    imester
    -1.71
    ptive
    -1.58
    incial
    -1.48
    uctor
    -1.43
    vernment
    -1.41
    artment
    -1.36
    umatic
    -1.27
    機
    -1.25
    bernatorial
    -1.25
    ngth
    -1.24
    POSITIVE LOGITS
     Lovecraft
    1.41
     poetry
    1.39
     Sabbath
    1.36
     solitude
    1.35
     Whedon
    1.33
     Elves
    1.31
     idols
    1.31
     Harley
    1.31
     Zion
    1.30
     gif
    1.30
    Activations Density 0.061%

    No Known Activations