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. 22473
    Prev
    Next
    INDEX
    Explanations

    people's names, organizations, and news-related keywords

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of the NBC network and associated content

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.07
    1:0.03
    2:0.29
    3:0.07
    4:0.11
    5:0.07
    6:0.03
    7:0.02
    8:0.05
    9:0.12
    10:0.05
    11:0.02
    Negative Logits
     裏�
    -1.38
     actionGroup
    -1.24
    �
    -1.23
     cig
    -1.22
     srfAttach
    -1.19
    ��
    -1.18
    ¯
    -1.11
    gie
    -1.07
     largeDownload
    -1.07
     bitten
    -1.07
    POSITIVE LOGITS
    iland
    1.30
    ource
    1.24
    ETH
    1.23
    APH
    1.20
    amara
    1.19
     CLSID
    1.18
    ashtra
    1.15
    WARE
    1.15
    akery
    1.14
     affiliate
    1.14
    Activations Density 0.010%

    No Known Activations