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. 3-ATT-KK
    6. 10390
    Prev
    Next
    INDEX
    Explanations

    components related to emotional or personal insights and reflections

    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
    0:0.07
    1:0.05
    2:0.07
    3:0.02
    4:0.27
    5:0.11
    6:0.07
    7:0.05
    8:0.07
    9:0.02
    10:0.08
    11:0.07
    Negative Logits
     Hut
    -1.69
     Provided
    -1.68
     Mechdragon
    -1.64
     Martial
    -1.64
     coron
    -1.61
    ulic
    -1.54
    ��
    -1.45
     Airl
    -1.44
    anwhile
    -1.41
     crem
    -1.41
    POSITIVE LOGITS
    req
    1.62
    ractions
    1.58
    genre
    1.56
    uracy
    1.50
    abulary
    1.46
    Suggest
    1.45
    Time
    1.45
    Reader
    1.45
    Reply
    1.44
     Lerner
    1.44
    Activations Density 0.099%

    No Known Activations