© 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. 10-ATT-KK
    11. 9052
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to environmental emissions and their scientific analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.19
    2:0.12
    3:0.06
    4:0.05
    5:0.04
    6:0.07
    7:0.07
    8:0.05
    9:0.04
    10:0.14
    11:0.04
    Negative Logits
     Ax
    -3.08
     Scal
    -3.02
     Ü
    -2.83
     Sche
    -2.82
     Mac
    -2.76
     multic
    -2.67
     Pole
    -2.61
     Macron
    -2.60
     ancestral
    -2.60
     Elven
    -2.59
    POSITIVE LOGITS
     NO
    5.46
    NO
    5.21
     YES
    3.98
    YES
    3.45
    ksh
    3.19
    KN
    3.11
     Nope
    3.07
    DO
    3.06
     Naomi
    3.03
    OH
    2.94
    Activations Density 0.002%

    No Known Activations