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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10349
    Prev
    Next
    INDEX
    Explanations

    phrases indicating formal reviews or assessments

    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
    0:0.02
    1:0.03
    2:0.04
    3:0.30
    4:0.02
    5:0.03
    6:0.07
    7:0.15
    8:0.04
    9:0.10
    10:0.07
    11:0.10
    Negative Logits
    ulhu
    -1.44
    imeters
    -1.35
    ���
    -1.34
    カ
    -1.32
    ����
    -1.30
    ppa
    -1.25
    agne
    -1.24
    inches
    -1.20
    フォ
    -1.18
    atos
    -1.13
    POSITIVE LOGITS
     agre
    1.49
    ommel
    1.39
     antioxid
    1.30
     pse
    1.30
    DragonMagazine
    1.27
     opin
    1.25
    essional
    1.25
     Merge
    1.23
     dossier
    1.21
     LinkedIn
    1.20
    Activations Density 0.014%

    No Known Activations