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. 5-ATT-KK
    6. 2826
    Prev
    Next
    INDEX
    Explanations

    proper names, especially those of notable individuals

    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
    1:0.03
    2:0.05
    3:0.06
    4:0.05
    5:0.05
    6:0.40
    7:0.04
    8:0.06
    9:0.08
    10:0.06
    11:0.04
    Negative Logits
    monary
    -1.31
     scanner
    -1.28
    imately
    -1.28
    ificantly
    -1.27
    inally
    -1.24
     mileage
    -1.21
    ️
    -1.20
    ashtra
    -1.20
    itals
    -1.17
     scams
    -1.16
    POSITIVE LOGITS
    cknow
    1.44
     Pearce
    1.43
    combe
    1.35
    rosso
    1.34
    ケ
    1.32
    brook
    1.30
    ��
    1.29
    テ
    1.28
    uci
    1.27
    mberg
    1.26
    Activations Density 0.011%

    No Known Activations