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. 22217
    Prev
    Next
    INDEX
    Explanations

    references to various types of parts and their roles in objects or systems

    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
    0:0.06
    1:0.04
    2:0.14
    3:0.06
    4:0.04
    5:0.10
    6:0.03
    7:0.03
    8:0.06
    9:0.27
    10:0.08
    11:0.03
    Negative Logits
    \\\\\\\\
    -1.27
    Merit
    -1.18
    ヤ
    -1.18
    itarian
    -1.17
    actionDate
    -1.16
    partisan
    -1.16
    iHUD
    -1.15
    ploy
    -1.12
    chieve
    -1.12
    arty
    -1.10
    POSITIVE LOGITS
     dehyd
    1.25
     oxid
    1.20
     zip
    1.18
    ulia
    1.17
     contrace
    1.16
     fermentation
    1.16
     perish
    1.16
     airflow
    1.16
     mos
    1.14
     propagate
    1.12
    Activations Density 0.021%

    No Known Activations