© 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. 5-ATT-KK
    11. 39484
    Prev
    Next
    INDEX
    Explanations

    references to approval processes and bureaucratic actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.06
    3:0.07
    4:0.08
    5:0.03
    6:0.06
    7:0.38
    8:0.04
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
    emetery
    -1.91
    izoph
    -1.77
     Leaves
    -1.76
     Alive
    -1.75
     Flags
    -1.67
    \">
    -1.67
     Deaths
    -1.67
    alach
    -1.64
     [-
    -1.62
    sterdam
    -1.62
    POSITIVE LOGITS
     tighter
    1.73
     Patel
    1.60
     clamp
    1.59
     pinch
    1.56
     tougher
    1.56
     inconsist
    1.52
     dated
    1.52
     watered
    1.49
     judgement
    1.48
     stringent
    1.47
    Activations Density 0.001%

    No Known Activations