© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 12621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating criticism or disappointment in Hollywood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.06
    2:0.04
    3:0.08
    4:0.05
    5:0.02
    6:0.10
    7:0.16
    8:0.01
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     Labrador
    -3.36
     Ö
    -3.12
    QL
    -2.66
     YPG
    -2.62
     PKK
    -2.52
     Burlington
    -2.48
     Panc
    -2.46
     Portsmouth
    -2.44
    �
    -2.43
     Nato
    -2.41
    POSITIVE LOGITS
     Hollywood
    5.46
    ollywood
    4.40
     Beverly
    4.24
     actresses
    4.18
     Oscars
    3.71
     Weinstein
    3.66
     MGM
    3.57
     Celeb
    3.55
     Judd
    3.30
     movies
    3.29
    Activations Density 0.018%

    No Known Activations