© 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. 43472
    Prev
    Next
    INDEX
    Explanations

    key concepts related to technology and innovation in various industries

    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
    0:0.05
    1:0.06
    2:0.03
    3:0.03
    4:0.02
    5:0.45
    6:0.03
    7:0.01
    8:0.04
    9:0.09
    10:0.08
    11:0.04
    Negative Logits
     regret
    -1.80
     Quake
    -1.57
     regrets
    -1.52
     PAY
    -1.50
    Australian
    -1.47
    ONDON
    -1.41
     regretted
    -1.40
    76561
    -1.40
    uploads
    -1.39
     disappoint
    -1.36
    POSITIVE LOGITS
    owship
    1.60
     Solution
    1.50
    tera
    1.47
     Essentially
    1.46
    olia
    1.40
     Generator
    1.40
    urat
    1.38
     mode
    1.38
    ostic
    1.36
     Doctrine
    1.35
    Activations Density 0.541%

    No Known Activations