© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 17261
    Prev
    Next
    INDEX
    Explanations

    references to environmental or technological innovations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.15
    1:0.14
    2:0.08
    3:0.06
    4:0.04
    5:0.02
    6:0.11
    7:0.15
    8:0.02
    9:0.03
    10:0.12
    11:0.04
    Negative Logits
    razil
    -2.70
    anchester
    -2.59
    �
    -2.51
    FW
    -2.45
     Guam
    -2.44
    EVA
    -2.43
    CG
    -2.38
    使
    -2.35
    inoa
    -2.30
     Ada
    -2.29
    POSITIVE LOGITS
     Spect
    7.30
    Spect
    6.34
     spect
    4.98
    spect
    4.34
     Spectre
    4.27
     Spectrum
    4.16
     spectral
    3.81
     Ast
    3.23
    Ast
    2.99
     Phantom
    2.85
    Activations Density 0.003%

    No Known Activations