© 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. 23128
    Prev
    Next
    INDEX
    Explanations

    references to specific colors or attributes of objects

    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
    1:0.11
    2:0.07
    3:0.07
    4:0.06
    5:0.04
    6:0.08
    7:0.07
    8:0.05
    9:0.04
    10:0.12
    11:0.08
    Negative Logits
     JC
    -3.08
     Normandy
    -3.01
     interpol
    -2.93
     GG
    -2.92
     Yo
    -2.90
     Rah
    -2.83
    cheat
    -2.83
     AJ
    -2.82
     Slaughter
    -2.82
     Houth
    -2.80
    POSITIVE LOGITS
     bulbs
    5.70
     bulb
    5.29
     tul
    3.62
     lamps
    3.34
     cloves
    3.13
     Stub
    3.12
    escent
    3.11
     filament
    3.10
     lamp
    3.09
    sighted
    3.08
    Activations Density 0.001%

    No Known Activations