© 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. 39486
    Prev
    Next
    INDEX
    Explanations

    mentions of parties involved in legal or business contexts

    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
    0:0.01
    1:0.01
    2:0.09
    3:0.07
    4:0.42
    5:0.02
    6:0.07
    7:0.08
    8:0.04
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
     Passage
    -1.64
     Cups
    -1.52
     crossover
    -1.51
     rewrite
    -1.47
     endings
    -1.46
    �
    -1.45
    ゼウス
    -1.43
     footprint
    -1.42
     gigs
    -1.41
     review
    -1.38
    POSITIVE LOGITS
    atel
    1.86
    ntil
    1.85
    olutely
    1.77
    ortunately
    1.63
     Blasio
    1.62
     discouraged
    1.61
    ateurs
    1.56
    ociated
    1.54
    dq
    1.52
    rust
    1.51
    Activations Density 0.001%

    No Known Activations