© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 17135
    Prev
    Next
    INDEX
    Explanations

    concepts related to authority and control within societal structures

    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
    0:0.02
    1:0.02
    2:0.02
    3:0.05
    4:0.04
    5:0.17
    6:0.03
    7:0.04
    8:0.02
    9:0.45
    10:0.02
    11:0.08
    Negative Logits
     sounding
    -2.17
     chanted
    -2.16
     smelling
    -2.15
     upbeat
    -2.06
    omas
    -2.06
     noisy
    -2.02
     colourful
    -2.02
     cheer
    -2.01
     sampled
    -2.00
     cheerful
    -1.99
    POSITIVE LOGITS
    ailable
    2.56
    thood
    2.46
     Allows
    2.35
     :=
    2.31
     override
    2.31
     [+
    2.25
    around
    2.25
    over
    2.24
    Ability
    2.22
     Immunity
    2.14
    Activations Density 0.135%

    No Known Activations