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. 2-ATT-KK
    6. 22444
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to government policies or organizational structures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.07
    3:0.25
    4:0.04
    5:0.09
    6:0.03
    7:0.07
    8:0.05
    9:0.05
    10:0.15
    11:0.08
    Negative Logits
    arov
    -1.23
    anton
    -1.21
    ���
    -1.17
    ��
    -1.16
    cephal
    -1.14
     Jinn
    -1.12
    �
    -1.12
    �士
    -1.06
    uve
    -1.05
    uph
    -1.05
    POSITIVE LOGITS
     counterparts
    2.13
     selves
    2.04
     brethren
    1.51
     holdings
    1.30
     counterpart
    1.27
     portfolio
    1.26
     peers
    1.21
     asses
    1.16
    respective
    1.15
     equivalents
    1.14
    Activations Density 0.348%

    No Known Activations