© 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. 19430
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "on" to signify focus or emphasis in various contexts

    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
    0:0.02
    1:0.02
    2:0.07
    3:0.06
    4:0.15
    5:0.02
    6:0.09
    7:0.18
    8:0.06
    9:0.04
    10:0.11
    11:0.14
    Negative Logits
    ��
    -1.46
    sche
    -1.35
    Catalog
    -1.35
    mr
    -1.31
    quarter
    -1.30
    theless
    -1.29
    �
    -1.29
    olver
    -1.27
    �
    -1.24
    deal
    -1.24
    POSITIVE LOGITS
     votes
    1.42
     exhaustion
    1.37
     scraps
    1.34
     merits
    1.32
     arbitrary
    1.32
    aughs
    1.32
     differences
    1.32
     bursts
    1.30
     confessions
    1.29
     hears
    1.27
    Activations Density 0.017%

    No Known Activations