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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10060
    Prev
    Next
    INDEX
    Explanations

    elements related to social interactions and relationships, particularly involving power dynamics and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.06
    2:0.13
    3:0.08
    4:0.02
    5:0.05
    6:0.09
    7:0.07
    8:0.18
    9:0.05
    10:0.12
    11:0.09
    Negative Logits
    hyde
    -0.94
    ��
    -0.91
    Language
    -0.87
    insula
    -0.86
    Border
    -0.86
    ourt
    -0.86
    rue
    -0.84
    ships
    -0.82
    Environment
    -0.82
    ept
    -0.82
    POSITIVE LOGITS
     exploded
    0.84
     stakes
    0.82
     replaced
    0.82
     belonged
    0.79
     convertible
    0.77
     interchangeable
    0.76
     belongs
    0.74
     specializes
    0.73
     premiered
    0.73
     collided
    0.73
    Activations Density 0.191%

    No Known Activations