© 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. 46776
    Prev
    Next
    INDEX
    Explanations

    references to veterans and their experiences, particularly relating to health, support, and their transition to civilian life

    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
    1:0.01
    2:0.05
    3:0.07
    4:0.04
    5:0.05
    6:0.07
    7:0.05
    8:0.04
    9:0.10
    10:0.24
    11:0.23
    Negative Logits
    cci
    -1.33
    seless
    -1.29
     Kinnikuman
    -1.27
    staff
    -1.17
    ujah
    -1.17
    戦
    -1.17
    ament
    -1.16
    rolet
    -1.16
     Commando
    -1.11
    govtrack
    -1.10
    POSITIVE LOGITS
     chemically
    1.30
     chromosomes
    1.29
    ociate
    1.25
    rencies
    1.25
     hormone
    1.16
    imilar
    1.13
     illegally
    1.12
     biologically
    1.11
     hormones
    1.11
    urities
    1.10
    Activations Density 0.028%

    No Known Activations