© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43722
    Prev
    Next
    INDEX
    Explanations

    neologisms or terms that signify change or evolution, particularly regarding historical contexts

    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
    0:0.03
    1:0.02
    2:0.08
    3:0.06
    4:0.08
    5:0.03
    6:0.34
    7:0.05
    8:0.04
    9:0.05
    10:0.12
    11:0.06
    Negative Logits
     Unloaded
    -1.54
    rored
    -1.52
    POR
    -1.47
    IUM
    -1.40
    66666666
    -1.39
    votes
    -1.38
    Available
    -1.37
    afety
    -1.37
    ongyang
    -1.36
    レ
    -1.35
    POSITIVE LOGITS
     narratives
    1.59
     traditions
    1.53
    ivism
    1.52
    ivist
    1.50
     nostalg
    1.49
     Celebration
    1.48
     sensibilities
    1.48
     renaissance
    1.46
     histor
    1.45
     Romantic
    1.44
    Activations Density 0.001%

    No Known Activations