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. 9-ATT-KK
    6. 7568
    Prev
    Next
    INDEX
    Explanations

    references to literary works and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.03
    2:0.06
    3:0.05
    4:0.05
    5:0.07
    6:0.09
    7:0.06
    8:0.28
    9:0.06
    10:0.02
    11:0.03
    Negative Logits
    ghai
    -3.91
     Cao
    -3.80
     Huawei
    -3.53
     Xin
    -3.47
    Chinese
    -3.22
     convent
    -3.07
    ancial
    -2.91
     Qi
    -2.89
     Quan
    -2.89
    avez
    -2.88
    POSITIVE LOGITS
     Sponge
    6.33
     Homer
    6.16
     Simpsons
    5.39
     Squid
    5.11
     Moe
    4.89
     Springfield
    4.43
     Nickel
    4.39
     Bart
    4.27
     Simpson
    3.86
    ikini
    3.84
    Activations Density 0.010%

    No Known Activations