© 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. 5573
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a decrease or failure

    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
    0:0.07
    1:0.08
    2:0.09
    3:0.08
    4:0.07
    5:0.08
    6:0.09
    7:0.08
    8:0.07
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    ostics
    -3.24
    ertodd
    -3.13
    othermal
    -2.70
    タ
    -2.64
    cells
    -2.60
    cerned
    -2.60
    ═
    -2.59
    ardo
    -2.50
    ivating
    -2.48
    ctuary
    -2.46
    POSITIVE LOGITS
     Canary
    2.93
     Kenn
    2.79
     fortnight
    2.67
     TS
    2.65
     CPC
    2.63
     CLS
    2.63
     behavioural
    2.56
     Nasa
    2.56
     pigeon
    2.54
     colour
    2.52
    Activations Density 0.000%

    No Known Activations