© 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 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. 28066
    Prev
    Next
    INDEX
    Explanations

    references to interpersonal relationships and social dynamics

    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
    0:0.01
    1:0.01
    2:0.15
    3:0.11
    4:0.35
    5:0.03
    6:0.05
    7:0.05
    8:0.06
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     respons
    -1.53
     antidote
    -1.43
     handwriting
    -1.42
     tears
    -1.38
     markings
    -1.37
     retract
    -1.37
     favourites
    -1.36
    rection
    -1.35
     ink
    -1.32
     redund
    -1.32
    POSITIVE LOGITS
    worm
    1.55
    justice
    1.45
    worms
    1.43
     Achievements
    1.38
     tenure
    1.35
     Diseases
    1.34
    gal
    1.34
    龍喚士
    1.31
    POST
    1.30
     Recent
    1.28
    Activations Density 0.145%

    No Known Activations