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

    Neuronpedia

    APICircuit 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. 8326
    Prev
    Next
    INDEX
    Explanations

    references to Eastern European regions and cultures

    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
    1:0.06
    2:0.09
    3:0.19
    4:0.04
    5:0.06
    6:0.06
    7:0.13
    8:0.10
    9:0.06
    10:0.06
    11:0.05
    Negative Logits
    ritical
    -1.23
    aucuses
    -1.21
    reditary
    -1.21
    catentry
    -1.16
     pregnancies
    -1.15
    iasm
    -1.14
    ascade
    -1.12
     notice
    -1.10
     flashbacks
    -1.09
    ��
    -1.08
    POSITIVE LOGITS
    ュ
    1.20
    tyard
    1.18
    Tes
    1.16
    �
    1.07
    л
    1.04
     damned
    1.03
    м
    1.00
     ACTIONS
    1.00
    fecture
    0.99
    Catal
    0.99
    Activations Density 0.004%

    No Known Activations