© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37554
    Prev
    Next
    INDEX
    Explanations

    information related to nuclear reactors and their operational status

    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
    1:0.01
    2:0.09
    3:0.13
    4:0.06
    5:0.06
    6:0.02
    7:0.05
    8:0.05
    9:0.11
    10:0.23
    11:0.11
    Negative Logits
    hate
    -1.42
     hates
    -1.41
     misinterpret
    -1.41
     offended
    -1.39
     subconscious
    -1.38
     rant
    -1.35
     Gamergate
    -1.34
    ophobia
    -1.33
     oppressed
    -1.33
    ghazi
    -1.30
    POSITIVE LOGITS
     upgr
    1.77
     commercially
    1.54
     replacements
    1.49
     upgrades
    1.48
     feasibility
    1.44
    undai
    1.35
     prototypes
    1.35
     operational
    1.35
     facilities
    1.28
     TBA
    1.28
    Activations Density 0.575%

    No Known Activations