© 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. 4457
    Prev
    Next
    INDEX
    Explanations

    instances of the placeholder "Ċ" indicating a reference or a section mark within a 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
    1:0.04
    2:0.05
    3:0.12
    4:0.08
    5:0.08
    6:0.08
    7:0.03
    8:0.09
    9:0.16
    10:0.11
    11:0.07
    Negative Logits
    artifacts
    -1.38
     simulac
    -1.35
     centrally
    -1.31
     heir
    -1.29
     footprint
    -1.29
     scaff
    -1.29
     inheritance
    -1.25
     descendants
    -1.24
     metic
    -1.22
     neighb
    -1.22
    POSITIVE LOGITS
    Words
    1.58
     laughter
    1.39
     applause
    1.34
     Reply
    1.33
    Clar
    1.33
    Talking
    1.28
    igh
    1.28
    CNN
    1.27
    assion
    1.26
    Translation
    1.25
    Activations Density 0.104%

    No Known Activations