© 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. 43812
    Prev
    Next
    INDEX
    Explanations

    phrases related to the nature of various missions or operations

    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
    1:0.02
    2:0.12
    3:0.12
    4:0.07
    5:0.04
    6:0.04
    7:0.23
    8:0.04
    9:0.04
    10:0.07
    11:0.13
    Negative Logits
    upiter
    -1.56
    reprene
    -1.55
    oglu
    -1.43
    oreal
    -1.42
    unky
    -1.39
     tremend
    -1.36
    obar
    -1.35
     inclined
    -1.34
    mounted
    -1.32
    icult
    -1.31
    POSITIVE LOGITS
    Format
    1.49
     Emanuel
    1.31
     Mulcair
    1.30
     PsyNet
    1.29
     Lau
    1.28
     Gael
    1.27
     Dill
    1.26
     Hil
    1.25
     Lancet
    1.23
    dylib
    1.22
    Activations Density 0.002%

    No Known Activations