© 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. 2-ATT-KK
    11. 12342
    Prev
    Next
    INDEX
    Explanations

    words related to military units

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.04
    2:0.17
    3:0.05
    4:0.05
    5:0.12
    6:0.02
    7:0.04
    8:0.05
    9:0.24
    10:0.07
    11:0.03
    Negative Logits
    dash
    -1.19
     Pastebin
    -1.18
    ゼ
    -1.16
    �
    -1.15
     gap
    -1.12
     omission
    -1.11
     pony
    -1.10
    platform
    -1.09
    ument
    -1.08
    ogyn
    -1.08
    POSITIVE LOGITS
    ngth
    1.82
    ioch
    1.51
    reciation
    1.51
     disbanded
    1.42
    hement
    1.41
    swick
    1.39
    arsity
    1.38
    alion
    1.37
    lication
    1.33
    incial
    1.32
    Activations Density 0.017%

    No Known Activations