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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 20247
    Prev
    Next
    INDEX
    Explanations

    instances of the symbol "âĢ", which appears to represent a specific formatting or encoding within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.15
    2:0.04
    3:0.08
    4:0.03
    5:0.18
    6:0.10
    7:0.01
    8:0.10
    9:0.06
    10:0.12
    11:0.05
    Negative Logits
    matic
    -1.62
     lottery
    -1.62
     monog
    -1.61
     suite
    -1.60
     incarn
    -1.49
     constitution
    -1.47
     Handbook
    -1.47
     jewels
    -1.45
    UAL
    -1.44
     bundle
    -1.40
    POSITIVE LOGITS
     Kurd
    1.76
    �
    1.72
     Ruk
    1.71
    escription
    1.71
     Rodrig
    1.65
    yden
    1.62
    arted
    1.61
    aughed
    1.60
    ��
    1.59
     Reeves
    1.58
    Activations Density 0.004%

    No Known Activations