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. 35759
    Prev
    Next
    INDEX
    Explanations

    phrases related to ease and simplicity in processes or tasks

    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
    1:0.01
    2:0.28
    3:0.09
    4:0.12
    5:0.04
    6:0.06
    7:0.08
    8:0.04
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
     Jol
    -1.62
     vom
    -1.56
     ASAP
    -1.52
     peacefully
    -1.51
     dies
    -1.47
    SN
    -1.47
     died
    -1.45
    �
    -1.44
     belonged
    -1.44
     deserves
    -1.43
    POSITIVE LOGITS
    ��
    1.94
    Course
    1.61
    natureconservancy
    1.49
    Interstitial
    1.49
    ibur
    1.48
    idious
    1.48
     millenn
    1.48
    teenth
    1.46
     sqor
    1.45
    ��極
    1.45
    Activations Density 0.002%

    No Known Activations