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

    Neuronpedia

    Jacobian LensNEW
    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. 42476
    Prev
    Next
    INDEX
    Explanations

    mentions of technology and personal experiences with its impact

    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
    1:0.01
    2:0.23
    3:0.20
    4:0.13
    5:0.02
    6:0.03
    7:0.08
    8:0.05
    9:0.05
    10:0.08
    11:0.05
    Negative Logits
     Variant
    -1.39
     undisclosed
    -1.34
     resid
    -1.28
    etheless
    -1.26
    iba
    -1.25
    kered
    -1.25
    enum
    -1.22
     Emir
    -1.21
    tip
    -1.21
     Jal
    -1.20
    POSITIVE LOGITS
     oneself
    2.54
     Yourself
    1.65
     injust
    1.60
     unnecessarily
    1.56
     responsibly
    1.56
     cheaply
    1.53
     versus
    1.52
     somehow
    1.48
    る
    1.46
     efficiently
    1.45
    Activations Density 0.749%

    No Known Activations