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. 3-ATT-KK
    6. 8436
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or activities, especially those that denote effort, struggle, or commitment

    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
    0:0.03
    1:0.03
    2:0.21
    3:0.06
    4:0.02
    5:0.03
    6:0.11
    7:0.18
    8:0.07
    9:0.06
    10:0.09
    11:0.06
    Negative Logits
    ht
    -1.11
    asio
    -1.03
    urion
    -0.99
     fielded
    -0.99
    auri
    -0.99
    ounter
    -0.96
    "},"
    -0.96
    atti
    -0.96
    atum
    -0.95
    option
    -0.93
    POSITIVE LOGITS
    YING
    0.90
     Ginny
    0.90
     selves
    0.90
    PsyNetMessage
    0.89
    ゴン
    0.89
     appe
    0.88
     counterparts
    0.88
     Mahjong
    0.88
     Pride
    0.87
     holy
    0.87
    Activations Density 0.178%

    No Known Activations