© 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. 46790
    Prev
    Next
    INDEX
    Explanations

    quantifiable statistics and figures related to fatalities and injuries

    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
    1:0.02
    2:0.10
    3:0.06
    4:0.09
    5:0.02
    6:0.27
    7:0.03
    8:0.08
    9:0.04
    10:0.12
    11:0.11
    Negative Logits
    ══
    -1.57
    isans
    -1.44
     Parables
    -1.44
     disclaimer
    -1.35
    ISION
    -1.35
    issance
    -1.29
     Thrones
    -1.28
     pse
    -1.28
     caveats
    -1.27
    yssey
    -1.26
    POSITIVE LOGITS
     discharged
    1.45
    bek
    1.40
    walking
    1.33
     humiliated
    1.32
     wounded
    1.24
    utonium
    1.22
     expelled
    1.21
     injure
    1.20
    ギ
    1.19
     reven
    1.19
    Activations Density 0.028%

    No Known Activations