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. 8629
    Prev
    Next
    INDEX
    Explanations

    references to announcements or mentions of products and quantities in the context of consumer goods

    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
    0:0.01
    1:0.03
    2:0.09
    3:0.28
    4:0.01
    5:0.02
    6:0.05
    7:0.14
    8:0.03
    9:0.15
    10:0.06
    11:0.06
    Negative Logits
    ources
    -1.40
    apter
    -1.39
    sembly
    -1.35
    udeb
    -1.34
    parable
    -1.30
    anchester
    -1.25
    nea
    -1.24
    isphere
    -1.23
    atisf
    -1.22
    osaurus
    -1.19
    POSITIVE LOGITS
     WATCHED
    1.60
    士
    1.28
     laun
    1.28
    ガ
    1.27
    NetMessage
    1.19
    Language
    1.13
     Dimensions
    1.13
    Interstitial
    1.13
    ドラ
    1.12
     裏�
    1.11
    Activations Density 0.001%

    No Known Activations