© 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. 41974
    Prev
    Next
    INDEX
    Explanations

    topics related to fishing practices, catch regulations, and their impacts on marine life

    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
    1:0.02
    2:0.04
    3:0.06
    4:0.04
    5:0.05
    6:0.03
    7:0.05
    8:0.03
    9:0.08
    10:0.35
    11:0.19
    Negative Logits
     Doodle
    -1.23
     Memory
    -1.23
     mathematic
    -1.21
     braces
    -1.21
     Unicode
    -1.19
    Disk
    -1.18
     coma
    -1.17
    socket
    -1.16
     Transform
    -1.15
    isexual
    -1.14
    POSITIVE LOGITS
    istration
    1.32
     livelihood
    1.28
     fees
    1.24
    ateurs
    1.22
     profits
    1.22
    Companies
    1.21
     crews
    1.20
    ewater
    1.19
     licences
    1.17
     prosecutions
    1.14
    Activations Density 0.194%

    No Known Activations