© 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. 39795
    Prev
    Next
    INDEX
    Explanations

    key terms associated with roles and titles in various contexts, especially within entertainment and media

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.04
    4:0.04
    5:0.02
    6:0.41
    7:0.10
    8:0.02
    9:0.03
    10:0.10
    11:0.08
    Negative Logits
    usercontent
    -1.56
    istas
    -1.48
    erella
    -1.45
    cdn
    -1.40
    igans
    -1.31
    edin
    -1.31
    raq
    -1.26
    conn
    -1.25
    gur
    -1.22
    agascar
    -1.21
    POSITIVE LOGITS
     Judgment
    1.20
    haar
    1.19
     subtitle
    1.18
     Secondary
    1.18
     Atkinson
    1.16
     Layer
    1.15
    itles
    1.14
     nobility
    1.13
     classification
    1.12
     Hamm
    1.11
    Activations Density 0.005%

    No Known Activations