© 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. 28469
    Prev
    Next
    INDEX
    Explanations

    language constructs with specific phonetic patterns or combinations of letters

    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
    1:0.01
    2:0.07
    3:0.05
    4:0.06
    5:0.03
    6:0.45
    7:0.03
    8:0.05
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    POSE
    -1.41
    olesterol
    -1.39
    Hit
    -1.31
    pload
    -1.30
    edIn
    -1.28
    lamm
    -1.27
     Cheong
    -1.25
    piece
    -1.23
    onday
    -1.21
     Pradesh
    -1.20
    POSITIVE LOGITS
    anchester
    1.83
    geist
    1.43
    án
    1.39
     CU
    1.28
     Asylum
    1.23
    andom
    1.22
     Incarn
    1.22
    ante
    1.22
    aires
    1.22
    ibly
    1.21
    Activations Density 0.001%

    No Known Activations