© 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. 10-ATT-KK
    11. 7846
    Prev
    Next
    INDEX
    Explanations

    quantitative loss data, particularly related to military and operational contexts

    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
    0:0.06
    1:0.23
    2:0.04
    3:0.13
    4:0.10
    5:0.03
    6:0.09
    7:0.13
    8:0.03
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    Standing
    -2.74
    Clean
    -2.63
    Direct
    -2.44
    �
    -2.34
    formance
    -2.32
     Direct
    -2.26
     Ready
    -2.25
     arrang
    -2.19
    Express
    -2.18
    Pro
    -2.16
    POSITIVE LOGITS
     lost
    5.78
     lose
    5.32
     loss
    5.22
     losses
    5.14
    lost
    5.13
     losing
    5.06
     loses
    4.93
    loss
    4.83
     Loss
    4.76
     Lose
    4.43
    Activations Density 0.115%

    No Known Activations