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. 3-ATT-KK
    6. 7946
    Prev
    Next
    INDEX
    Explanations

    references to Kurdish and Indian identities within a political context

    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
    0:0.03
    1:0.04
    2:0.06
    3:0.13
    4:0.02
    5:0.02
    6:0.27
    7:0.07
    8:0.07
    9:0.06
    10:0.05
    11:0.13
    Negative Logits
    efully
    -1.44
    staking
    -1.43
     ********************************
    -1.43
     ├──
    -1.40
     �
    -1.30
    ginx
    -1.30
    ciation
    -1.29
    acity
    -1.27
    ounded
    -1.27
     pg
    -1.26
    POSITIVE LOGITS
     Croat
    1.58
    anian
    1.57
    wagen
    1.42
     Gree
    1.38
     hostilities
    1.35
     Rebellion
    1.29
     Blazers
    1.28
     offensive
    1.28
     contingent
    1.28
    Knight
    1.22
    Activations Density 0.017%

    No Known Activations