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. 3-ATT-KK
    6. 8359
    Prev
    Next
    INDEX
    Explanations

    specific entities, titles, and important aspects within various contexts like politics, media, and online interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.05
    2:0.27
    3:0.03
    4:0.02
    5:0.03
    6:0.06
    7:0.07
    8:0.09
    9:0.04
    10:0.07
    11:0.20
    Negative Logits
    krit
    -1.25
    ��
    -1.23
    steamapps
    -1.21
    gging
    -1.20
     Shirley
    -1.19
     srfAttach
    -1.16
    NetMessage
    -1.14
    AMY
    -1.12
    glomer
    -1.10
    rosis
    -1.07
    POSITIVE LOGITS
     differs
    1.33
    estamp
    1.24
    yip
    1.19
     differed
    1.17
     viz
    1.16
     compares
    1.15
     describes
    1.15
     defines
    1.10
     translates
    1.10
    ishes
    1.09
    Activations Density 0.029%

    No Known Activations