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

    Neuronpedia

    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. 10-ATT-KK
    11. 15427
    Prev
    Next
    INDEX
    Explanations

    warnings and advice related to safety and preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    3:0.07
    4:0.08
    5:0.41
    6:0.02
    7:0.03
    8:0.02
    9:0.19
    10:0.02
    11:0.04
    Negative Logits
     culminated
    -3.25
     became
    -3.16
     emerged
    -3.10
     vanished
    -3.10
     amounted
    -3.04
    could
    -2.88
     soared
    -2.85
     morphed
    -2.79
     transpired
    -2.79
     disappeared
    -2.73
    POSITIVE LOGITS
     BEFORE
    6.29
     ASAP
    5.19
     before
    5.04
     beforehand
    4.86
     yourselves
    4.49
     yourself
    4.28
     FIRST
    4.27
    before
    4.23
     whenever
    4.12
     prior
    4.00
    Activations Density 0.615%

    No Known Activations