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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19105
    Prev
    Next
    INDEX
    Explanations

    mentions of Facebook and its operations related to social networking

    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
    0:0.02
    1:0.01
    2:0.04
    3:0.05
    4:0.03
    5:0.07
    6:0.04
    7:0.02
    8:0.04
    9:0.07
    10:0.40
    11:0.14
    Negative Logits
    iHUD
    -1.67
     Alz
    -1.65
     Beir
    -1.50
    tnc
    -1.47
    aina
    -1.47
    Ton
    -1.44
     Leth
    -1.42
    rieg
    -1.40
    channelAvailability
    -1.40
     Luffy
    -1.39
    POSITIVE LOGITS
     famously
    1.58
     Logo
    1.55
     Admin
    1.55
     notoriously
    1.51
     CEO
    1.49
     monopoly
    1.41
     supposedly
    1.39
     executives
    1.38
     Employees
    1.38
     monopol
    1.38
    Activations Density 0.134%

    No Known Activations