© 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. 43516
    Prev
    Next
    INDEX
    Explanations

    copyright-related phrases and publication years

    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
    0:0.01
    1:0.01
    2:0.12
    3:0.17
    4:0.05
    5:0.02
    6:0.06
    7:0.17
    8:0.03
    9:0.04
    10:0.06
    11:0.22
    Negative Logits
    iversity
    -1.48
    SourceFile
    -1.34
    prints
    -1.34
    Reviewer
    -1.29
    esty
    -1.29
    mite
    -1.26
    YC
    -1.26
     fees
    -1.26
    conservancy
    -1.26
    Atl
    -1.25
    POSITIVE LOGITS
    atile
    1.40
    oters
    1.39
    icians
    1.25
    Leader
    1.24
    states
    1.24
    ammers
    1.20
    bind
    1.19
     Mew
    1.19
     depress
    1.18
     Belarus
    1.17
    Activations Density 0.003%

    No Known Activations