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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 34676
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate presence or absence of noise and silence

    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
    0:0.03
    1:0.03
    2:0.14
    3:0.09
    4:0.10
    5:0.03
    6:0.12
    7:0.12
    8:0.06
    9:0.04
    10:0.07
    11:0.13
    Negative Logits
    ーン
    -1.63
     substituted
    -1.57
    ensis
    -1.56
    inventoryQuantity
    -1.54
    random
    -1.43
    only
    -1.38
    Rot
    -1.37
     apologized
    -1.36
     apologize
    -1.36
     replaced
    -1.36
    POSITIVE LOGITS
     potential
    1.38
     socially
    1.38
     lett
    1.36
    ]."
    1.31
    ],"
    1.30
     enthusi
    1.29
     essentials
    1.29
     workforce
    1.28
     microbi
    1.27
     academia
    1.26
    Activations Density 0.009%

    No Known Activations