Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10018
    Prev
    Next
    INDEX
    Explanations

    references to the 'purpose' of various systems, acts, or concepts

    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
    0:0.01
    1:0.02
    2:0.03
    3:0.27
    4:0.01
    5:0.02
    6:0.06
    7:0.21
    8:0.04
    9:0.03
    10:0.05
    11:0.19
    Negative Logits
    achus
    -1.40
    ashtra
    -1.38
    ebted
    -1.36
    ivia
    -1.35
    chuk
    -1.29
     Peninsula
    -1.26
    igers
    -1.23
     peninsula
    -1.19
    onia
    -1.19
    olia
    -1.19
    POSITIVE LOGITS
     Sacrifice
    1.23
    stay
    1.17
     reserv
    1.15
    Accessory
    1.14
     arrang
    1.13
     econom
    1.13
     Ramadan
    1.12
    ��
    1.10
     Swanson
    1.09
     stewards
    1.09
    Activations Density 0.008%

    No Known Activations