© 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. 5-ATT-KK
    11. 7670
    Prev
    Next
    INDEX
    Explanations

    commands and actions related to SQL updates and data manipulation

    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
    0:0.08
    1:0.03
    2:0.08
    3:0.12
    4:0.11
    5:0.06
    6:0.07
    7:0.04
    8:0.05
    9:0.09
    10:0.10
    11:0.11
    Negative Logits
    Reviewer
    -1.76
     behavi
    -1.61
     confir
    -1.60
     acknow
    -1.50
    utical
    -1.39
    ktop
    -1.36
     conclud
    -1.35
    theless
    -1.34
    duino
    -1.33
    ��
    -1.31
    POSITIVE LOGITS
    Status
    1.46
     ×
    1.39
     ZIP
    1.33
    HI
    1.33
     [(
    1.32
    /(
    1.31
    Prev
    1.30
     Begin
    1.20
    +(
    1.18
    Number
    1.18
    Activations Density 0.002%

    No Known Activations