© 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. 44894
    Prev
    Next
    INDEX
    Explanations

    terms indicating loss, urgency, and issues related to accountability

    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
    1:0.03
    2:0.24
    3:0.24
    4:0.06
    5:0.04
    6:0.11
    7:0.02
    8:0.04
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    ))))
    -1.33
    ennes
    -1.30
     Kyl
    -1.29
    )))
    -1.25
    oen
    -1.21
    ircraft
    -1.21
    alez
    -1.20
    ustomed
    -1.19
    overty
    -1.17
    Wi
    -1.16
    POSITIVE LOGITS
    ヘ
    1.57
    vr
    1.52
    す
    1.38
    �
    1.37
     Mermaid
    1.33
    thood
    1.30
    motion
    1.28
    quant
    1.28
    umbn
    1.27
     Yourself
    1.23
    Activations Density 0.240%

    No Known Activations