© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43177
    Prev
    Next
    INDEX
    Explanations

    negations or words indicating the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.01
    2:0.26
    3:0.11
    4:0.10
    5:0.04
    6:0.10
    7:0.05
    8:0.06
    9:0.07
    10:0.07
    11:0.04
    Negative Logits
     Scholarship
    -1.33
     Tradition
    -1.31
    phia
    -1.30
     Trophy
    -1.30
     Scholars
    -1.26
     Compan
    -1.25
     Charity
    -1.23
     Fund
    -1.21
     Programme
    -1.21
     Strip
    -1.20
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    1.57
    quit
    1.55
    wu
    1.32
    quished
    1.29
    arez
    1.28
    luaj
    1.27
    watch
    1.26
    youtu
    1.24
    watching
    1.23
    ready
    1.20
    Activations Density 0.013%

    No Known Activations