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. 18935
    Prev
    Next
    INDEX
    Explanations

    conditions or variables related to flags and settings in programming

    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
    0:0.05
    1:0.23
    2:0.04
    3:0.07
    4:0.04
    5:0.06
    6:0.10
    7:0.08
    8:0.06
    9:0.07
    10:0.08
    11:0.06
    Negative Logits
    ufact
    -2.14
    omorph
    -1.95
     perish
    -1.95
    ��
    -1.92
    odynam
    -1.85
     stret
    -1.85
     tissues
    -1.84
    cule
    -1.81
     Obj
    -1.80
    erto
    -1.80
    POSITIVE LOGITS
    isSpecialOrderable
    2.27
    option
    2.27
    oggles
    2.18
     perk
    2.03
     perks
    2.03
    olean
    2.00
    enabled
    1.95
    toggle
    1.91
     option
    1.90
     lantern
    1.86
    Activations Density 0.001%

    No Known Activations