© 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. 9-ATT-KK
    11. 5788
    Prev
    Next
    INDEX
    Explanations

    the word "down" in varying contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.07
    3:0.09
    4:0.08
    5:0.09
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     offence
    -3.04
     organis
    -2.88
     abolished
    -2.87
     deregulation
    -2.87
     Nato
    -2.82
     fascism
    -2.79
     disadvant
    -2.78
     fascist
    -2.77
     neo
    -2.75
     insurgent
    -2.72
    POSITIVE LOGITS
     Puzz
    4.03
     Flores
    2.96
    mire
    2.94
    bors
    2.92
     Rated
    2.88
     Posted
    2.81
     Pupp
    2.78
     [/
    2.74
     SUM
    2.67
    Todd
    2.56
    Activations Density 0.000%

    No Known Activations