© 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. 43864
    Prev
    Next
    INDEX
    Explanations

    phrases indicating compliance or fitness for specific roles or activities

    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
    0:0.02
    1:0.00
    2:0.07
    3:0.04
    4:0.07
    5:0.02
    6:0.41
    7:0.12
    8:0.03
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
    ベ
    -1.36
     haunt
    -1.29
     Ghosts
    -1.23
     cryptocurrencies
    -1.23
    mable
    -1.22
    wolves
    -1.21
    iatrics
    -1.21
     Dogs
    -1.20
     eBook
    -1.19
    rences
    -1.18
    POSITIVE LOGITS
    ��
    1.53
     Configuration
    1.29
     artic
    1.27
    ypes
    1.24
    bodied
    1.23
    rouse
    1.22
    ovo
    1.21
     Removal
    1.18
    enough
    1.17
     arri
    1.17
    Activations Density 0.004%

    No Known Activations