© 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. 10116
    Prev
    Next
    INDEX
    Explanations

    declarative statements related to police activities and interactions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.02
    1:0.02
    2:0.07
    3:0.09
    4:0.07
    5:0.02
    6:0.06
    7:0.21
    8:0.05
    9:0.05
    10:0.14
    11:0.17
    Negative Logits
    """
    -1.76
    76561
    -1.64
    ��
    -1.52
    DragonMagazine
    -1.49
    channelAvailability
    -1.48
     weap
    -1.42
    govtrack
    -1.40
    manager
    -1.34
    obyl
    -1.33
    \\\\\\\\
    -1.31
    POSITIVE LOGITS
     Corpus
    1.30
     Zurich
    1.24
     Sections
    1.22
     Nass
    1.18
     GER
    1.16
     Downing
    1.14
     Naj
    1.13
     Brune
    1.11
    ixir
    1.11
     Brass
    1.11
    Activations Density 0.029%

    No Known Activations