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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10239
    Prev
    Next
    INDEX
    Explanations

    references to parliamentary seats and electoral outcomes

    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
    2:0.05
    3:0.05
    4:0.03
    5:0.09
    6:0.05
    7:0.36
    8:0.06
    9:0.04
    10:0.07
    11:0.09
    Negative Logits
    lez
    -1.49
    ��
    -1.38
    DragonMagazine
    -1.38
    actionDate
    -1.35
    Pros
    -1.34
    gif
    -1.33
    aste
    -1.33
    YouTube
    -1.29
    rypt
    -1.27
    yrics
    -1.26
    POSITIVE LOGITS
     vacated
    1.84
     respectively
    1.66
     contiguous
    1.50
     narrower
    1.48
     discretionary
    1.47
     vacant
    1.44
     apiece
    1.39
     consecut
    1.37
     comfortably
    1.32
     (-
    1.30
    Activations Density 0.027%

    No Known Activations