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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7582
    Prev
    Next
    INDEX
    Explanations

    topics related to political figures and their 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
    0:0.02
    1:0.02
    2:0.21
    3:0.17
    4:0.06
    5:0.05
    6:0.05
    7:0.04
    8:0.07
    9:0.10
    10:0.09
    11:0.07
    Negative Logits
     athlet
    -1.51
     dwar
    -1.30
     debilitating
    -1.29
     permitting
    -1.28
     culminating
    -1.28
    ukemia
    -1.25
     sponsoring
    -1.25
     nefarious
    -1.24
    owship
    -1.22
     weaving
    -1.21
    POSITIVE LOGITS
    inventoryQuantity
    2.18
    エル
    1.60
    ?]
    1.48
    の�
    1.48
    将
    1.44
    ヘラ
    1.42
    ーク
    1.41
    Adds
    1.39
    ーン
    1.39
    =(
    1.38
    Activations Density 0.016%

    No Known Activations