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. 9230
    Prev
    Next
    INDEX
    Explanations

    terms related to 'Pokémon' and structures

    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
    0:0.04
    1:0.05
    2:0.21
    3:0.03
    4:0.02
    5:0.03
    6:0.05
    7:0.08
    8:0.04
    9:0.03
    10:0.31
    11:0.05
    Negative Logits
    ennes
    -2.46
    cas
    -2.34
    Cas
    -2.27
    pend
    -2.25
    asper
    -2.17
    igl
    -2.13
     Cas
    -2.10
    phas
    -2.07
    arde
    -2.06
    Pierre
    -2.01
    POSITIVE LOGITS
    U
    3.96
     U
    3.94
     Ug
    3.10
     Union
    3.08
     u
    3.06
     UA
    3.00
     UNITED
    2.98
     United
    2.86
     UW
    2.84
     Utt
    2.78
    Activations Density 0.003%

    No Known Activations