© 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. 23007
    Prev
    Next
    INDEX
    Explanations

    phrases related to keeping things connected or maintaining continuity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    key concepts related to coherence and continuity in narratives

    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
    1:0.02
    2:0.13
    3:0.07
    4:0.09
    5:0.10
    6:0.03
    7:0.02
    8:0.27
    9:0.06
    10:0.06
    11:0.02
    Negative Logits
    IAL
    -1.29
    �
    -1.26
    ��
    -1.25
    ��
    -1.23
    agents
    -1.16
    illon
    -1.16
    sts
    -1.16
    iots
    -1.12
    lass
    -1.12
    �
    -1.08
    POSITIVE LOGITS
    iquid
    1.38
     sidx
    1.13
     cozy
    1.13
    aeper
    1.12
    keleton
    1.12
     anecd
    1.10
    hare
    1.09
     tightly
    1.07
    weekly
    1.06
    lycer
    1.05
    Activations Density 0.007%

    No Known Activations