© 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. 2517
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ability or permission to perform actions

    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
    1:0.03
    2:0.06
    3:0.07
    4:0.10
    5:0.04
    6:0.09
    7:0.23
    8:0.05
    9:0.05
    10:0.08
    11:0.13
    Negative Logits
    aber
    -1.26
     backdrop
    -1.19
    bird
    -1.16
    grave
    -1.14
     unbel
    -1.11
     enqu
    -1.11
     puzz
    -1.10
    ware
    -1.10
     hotly
    -1.09
     tir
    -1.09
    POSITIVE LOGITS
     distribute
    1.35
     withstand
    1.34
     access
    1.33
     adequate
    1.27
    otonin
    1.26
     secure
    1.24
     afford
    1.23
     reproduce
    1.20
    aez
    1.20
     pass
    1.18
    Activations Density 0.035%

    No Known Activations