© 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. 46953
    Prev
    Next
    INDEX
    Explanations

    references to playful or interactive behaviors and relationships

    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
    0:0.01
    1:0.01
    2:0.11
    3:0.05
    4:0.26
    5:0.03
    6:0.08
    7:0.23
    8:0.02
    9:0.02
    10:0.05
    11:0.06
    Negative Logits
    VO
    -1.70
    ê
    -1.54
    buquerque
    -1.52
    �
    -1.50
    FIR
    -1.49
    ioxide
    -1.49
    ��
    -1.47
    advertising
    -1.44
    uala
    -1.44
    ablishment
    -1.40
    POSITIVE LOGITS
     boundaries
    1.99
     strengths
    1.72
     sensit
    1.61
     buttons
    1.59
     facets
    1.57
     dynamics
    1.56
     severity
    1.52
     nuance
    1.52
     slider
    1.52
     rug
    1.52
    Activations Density 0.016%

    No Known Activations