© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 21646
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to familial relationships and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.03
    2:0.11
    3:0.09
    4:0.03
    5:0.08
    6:0.05
    7:0.08
    8:0.04
    9:0.10
    10:0.20
    11:0.08
    Negative Logits
     HF
    -0.95
    cerning
    -0.93
     (~
    -0.87
    rush
    -0.87
     AR
    -0.80
     acron
    -0.79
     headline
    -0.79
     preced
    -0.76
     ROS
    -0.75
     backdrop
    -0.73
    POSITIVE LOGITS
    cknow
    1.08
    untarily
    1.03
    potion
    0.91
     kissed
    0.90
     sacrific
    0.88
     willingly
    0.86
     contrace
    0.85
    artifacts
    0.85
    ]."
    0.84
     repent
    0.81
    Activations Density 0.412%

    No Known Activations