© 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. 44068
    Prev
    Next
    INDEX
    Explanations

    references to the production and contributors of creative works, particularly in film and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.12
    1:0.04
    2:0.08
    3:0.11
    4:0.05
    5:0.07
    6:0.02
    7:0.02
    8:0.06
    9:0.14
    10:0.14
    11:0.11
    Negative Logits
    perty
    -1.18
    iji
    -1.18
    ð
    -1.16
    vernment
    -1.12
    vati
    -1.09
    peror
    -1.08
    wcsstore
    -1.08
    llor
    -1.07
    lyak
    -1.07
    ivan
    -1.05
    POSITIVE LOGITS
     extras
    1.24
     Preview
    1.21
     transl
    1.20
     Audio
    1.17
     Content
    1.15
     appl
    1.15
     Airl
    1.14
     transcription
    1.11
     Archive
    1.09
     preview
    1.06
    Activations Density 0.058%

    No Known Activations