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. 7-ATT-KK
    6. 9518
    Prev
    Next
    INDEX
    Explanations

    brands and models related to graphics cards and automotive technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.08
    2:0.04
    3:0.08
    4:0.14
    5:0.07
    6:0.08
    7:0.03
    8:0.07
    9:0.05
    10:0.06
    11:0.04
    Negative Logits
    isine
    -1.67
     ILCS
    -1.59
     deeds
    -1.54
    thia
    -1.52
     Azerb
    -1.48
     disappear
    -1.46
    DERR
    -1.46
    dinand
    -1.44
    alties
    -1.44
     agencies
    -1.43
    POSITIVE LOGITS
     resembles
    2.11
     utilizes
    2.03
     debuted
    2.02
     consists
    1.99
     embodies
    1.98
     weighs
    1.98
     combines
    1.96
     comprises
    1.95
     consumes
    1.93
     pictured
    1.92
    Activations Density 0.053%

    No Known Activations