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. 1-ATT-KK
    6. 6330
    Prev
    Next
    INDEX
    Explanations

    mentions of diversity in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.05
    2:0.04
    3:0.02
    4:0.06
    5:0.11
    6:0.23
    7:0.06
    8:0.03
    9:0.02
    10:0.04
    11:0.22
    Negative Logits
    hao
    -1.28
    VR
    -1.25
    orage
    -1.22
    iaz
    -1.13
    amphetamine
    -1.11
    Accessory
    -1.10
     =================================================================
    -1.08
    ��
    -1.07
     refill
    -1.06
     proc
    -1.06
    POSITIVE LOGITS
    kees
    1.52
    ken
    1.27
    itarian
    1.24
     Diversity
    1.23
     voices
    1.13
    ihara
    1.09
    folk
    1.08
     pronouns
    1.06
    bent
    1.06
     hat
    1.05
    Activations Density 0.020%

    No Known Activations