© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 35622
    Prev
    Next
    INDEX
    Explanations

    specific structure and syntax elements related to code or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.04
    2:0.10
    3:0.11
    4:0.05
    5:0.06
    6:0.03
    7:0.09
    8:0.05
    9:0.07
    10:0.18
    11:0.12
    Negative Logits
    hospital
    -1.26
     vacancies
    -1.25
    istrates
    -1.25
     warranties
    -1.24
     Houses
    -1.23
    emale
    -1.23
    ylum
    -1.22
    ewitness
    -1.21
     testifying
    -1.20
     remission
    -1.20
    POSITIVE LOGITS
    Buff
    1.36
     jQuery
    1.35
     embed
    1.31
    ��
    1.31
     blend
    1.28
    webkit
    1.25
    Animation
    1.25
     parser
    1.24
    engine
    1.23
    builder
    1.22
    Activations Density 0.001%

    No Known Activations