© 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. 40060
    Prev
    Next
    INDEX
    Explanations

    phrases related to lifting or removing restrictions, bans, or obstacles

    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
    0:0.03
    1:0.02
    2:0.05
    3:0.05
    4:0.13
    5:0.02
    6:0.06
    7:0.45
    8:0.02
    9:0.02
    10:0.05
    11:0.05
    Negative Logits
    alph
    -1.40
    00000000
    -1.36
    isers
    -1.34
     omission
    -1.33
    Ox
    -1.32
    0000000000000000
    -1.30
     rookies
    -1.28
     Cipher
    -1.26
     Conquest
    -1.26
     Convers
    -1.22
    POSITIVE LOGITS
    bright
    1.80
     veil
    1.76
     curtain
    1.71
     brighter
    1.65
     lid
    1.61
     spirits
    1.61
     gaze
    1.59
    ulic
    1.57
     folds
    1.55
     shine
    1.55
    Activations Density 0.010%

    No Known Activations