Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7503
    Prev
    Next
    INDEX
    Explanations

    references to storytelling and narrative elements

    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
    1:0.02
    2:0.12
    3:0.09
    4:0.13
    5:0.03
    6:0.05
    7:0.34
    8:0.02
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
    ワ
    -1.67
     speeds
    -1.62
     Zup
    -1.57
     Newport
    -1.52
    ISO
    -1.52
     Elections
    -1.51
    obal
    -1.43
    vironments
    -1.42
     distances
    -1.39
     cloaked
    -1.38
    POSITIVE LOGITS
     precedent
    1.67
     trend
    1.62
    backer
    1.59
    dogs
    1.58
    erva
    1.58
     favourites
    1.57
     disappoint
    1.57
     favorites
    1.56
    widget
    1.52
     filler
    1.52
    Activations Density 0.016%

    No Known Activations