© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 21461
    Prev
    Next
    INDEX
    Explanations

    references to money and financial transactions

    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
    0:0.07
    1:0.03
    2:0.21
    3:0.04
    4:0.26
    5:0.05
    6:0.03
    7:0.02
    8:0.06
    9:0.12
    10:0.04
    11:0.02
    Negative Logits
    ��
    -1.78
    ardless
    -1.64
    tumblr
    -1.41
     unfocusedRange
    -1.40
    xual
    -1.37
    ilib
    -1.31
    YN
    -1.29
    方
    -1.26
    ��
    -1.24
    ��
    -1.23
    POSITIVE LOGITS
    sylv
    1.46
     Alto
    1.42
     consolation
    1.37
     underdog
    1.19
     loser
    1.18
    tops
    1.17
    jong
    1.17
     hopped
    1.15
    ippi
    1.15
     rattled
    1.14
    Activations Density 0.001%

    No Known Activations