Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 3036
    Prev
    Next
    INDEX
    Explanations

    military-related terminology and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.04
    1:0.05
    2:0.07
    3:0.06
    4:0.07
    5:0.06
    6:0.26
    7:0.09
    8:0.04
    9:0.06
    10:0.08
    11:0.07
    Negative Logits
    omore
    -1.53
     woes
    -1.41
     womb
    -1.33
     liner
    -1.30
    bilt
    -1.29
     Dust
    -1.29
     jealous
    -1.28
     Reign
    -1.24
    mania
    -1.24
    ////////////////////////////////
    -1.24
    POSITIVE LOGITS
    letcher
    1.41
    eger
    1.39
    ggles
    1.38
     instruct
    1.36
    ogle
    1.32
    channel
    1.32
    cknow
    1.26
     Elk
    1.26
     advises
    1.25
     speaker
    1.23
    Activations Density 0.000%

    No Known Activations