© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 11970
    Prev
    Next
    INDEX
    Explanations

    specific references to power capacities and sources like wind, solar, nuclear, and natural gas

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.05
    1:0.07
    2:0.16
    3:0.10
    4:0.11
    5:0.08
    6:0.05
    7:0.06
    8:0.04
    9:0.14
    10:0.08
    11:0.03
    Negative Logits
     plagiar
    -1.37
     Canaan
    -1.36
     rituals
    -1.33
     clipboard
    -1.33
    ��
    -1.32
     treason
    -1.30
     ritual
    -1.28
     Bapt
    -1.25
     Rabb
    -1.23
     gag
    -1.23
    POSITIVE LOGITS
    −
    1.65
    indust
    1.33
    anchester
    1.30
    IUM
    1.28
    izontal
    1.27
    energy
    1.26
    ™:
    1.26
    izont
    1.26
    FIG
    1.25
    axis
    1.21
    Activations Density 0.006%

    No Known Activations