© 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. 19930
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal feelings and experiences

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.15
    4:0.05
    5:0.08
    6:0.13
    7:0.02
    8:0.04
    9:0.15
    10:0.09
    11:0.12
    Negative Logits
    etheless
    -1.68
     CLSID
    -1.57
    ebted
    -1.40
    Scroll
    -1.31
    edIn
    -1.20
     similarly
    -1.19
    AGES
    -1.18
     ≡
    -1.18
    KC
    -1.17
     裏覚醒
    -1.14
    POSITIVE LOGITS
    usterity
    1.45
    ..."
    1.34
     …"
    1.31
    !"
    1.29
     arrogance
    1.27
    .")
    1.25
     tough
    1.22
     relativity
    1.21
     blah
    1.20
     decriminal
    1.20
    Activations Density 0.192%

    No Known Activations