© 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. 45527
    Prev
    Next
    INDEX
    Explanations

    terms related to proper procedures and compliance in various contexts

    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
    1:0.00
    2:0.07
    3:0.05
    4:0.16
    5:0.02
    6:0.17
    7:0.26
    8:0.03
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
     Rouge
    -1.64
    zai
    -1.42
    utra
    -1.42
    pora
    -1.40
    Jet
    -1.37
    aris
    -1.37
    ships
    -1.36
    tumblr
    -1.33
    Dro
    -1.30
     Crate
    -1.27
    POSITIVE LOGITS
    enses
    1.60
    Rated
    1.53
     properly
    1.52
    ensible
    1.50
    ß
    1.47
    oler
    1.45
    balance
    1.44
    correct
    1.44
    agnetic
    1.43
     サーティワン
    1.41
    Activations Density 0.005%

    No Known Activations