© 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. 9-ATT-KK
    6. 21628
    Prev
    Next
    INDEX
    Explanations

    mentions of social media platforms or actions associated with sharing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.37
    2:0.02
    3:0.11
    4:0.02
    5:0.09
    6:0.01
    7:0.14
    8:0.02
    9:0.00
    10:0.13
    11:0.03
    Negative Logits
    very
    -2.81
    sell
    -2.38
    aged
    -2.34
    want
    -2.32
     80
    -2.28
     captcha
    -2.26
    cloth
    -2.20
     disagrees
    -2.19
     84
    -2.18
    seller
    -2.17
    POSITIVE LOGITS
    ッド
    2.61
     Leban
    2.55
     Quote
    2.40
    ��
    2.32
     dstg
    2.27
    iable
    2.25
    ranean
    2.19
    iably
    2.19
     thence
    2.19
    emouth
    2.18
    Activations Density 0.002%

    No Known Activations