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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7305
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating purpose or reason

    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
    0:0.01
    1:0.01
    2:0.04
    3:0.03
    4:0.15
    5:0.03
    6:0.31
    7:0.15
    8:0.04
    9:0.03
    10:0.04
    11:0.10
    Negative Logits
     PsyNet
    -1.67
     Shrine
    -1.51
    itch
    -1.29
     Crusher
    -1.27
     adam
    -1.23
     Leia
    -1.23
    kered
    -1.21
     Gamble
    -1.19
     recoil
    -1.19
     cellul
    -1.19
    POSITIVE LOGITS
    clud
    1.43
    olitan
    1.32
     refres
    1.30
     expel
    1.29
     apart
    1.26
     Finder
    1.24
    stop
    1.24
     topp
    1.22
    plet
    1.21
    uit
    1.19
    Activations Density 0.004%

    No Known Activations