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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21855
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals, particularly those mentioned in a context related to social issues or actions

    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
    0:0.09
    1:0.03
    2:0.28
    3:0.06
    4:0.15
    5:0.04
    6:0.03
    7:0.03
    8:0.07
    9:0.09
    10:0.06
    11:0.03
    Negative Logits
    etheless
    -1.32
     specificity
    -1.24
    owship
    -1.23
    yip
    -1.20
     Egyptians
    -1.18
     cov
    -1.14
    undown
    -1.11
     ANG
    -1.09
     Mexicans
    -1.08
     associations
    -1.07
    POSITIVE LOGITS
    lyn
    1.31
    ilee
    1.25
    gui
    1.20
    姫
    1.19
    装
    1.18
    gar
    1.16
    argo
    1.16
    yll
    1.15
    visor
    1.13
    hire
    1.12
    Activations Density 0.012%

    No Known Activations