© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 42568
    Prev
    Next
    INDEX
    Explanations

    conjunctions and references to political or social components

    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
    1:0.01
    2:0.07
    3:0.05
    4:0.05
    5:0.03
    6:0.33
    7:0.03
    8:0.04
    9:0.03
    10:0.14
    11:0.14
    Negative Logits
    oru
    -1.20
    ambers
    -1.19
    EEK
    -1.14
     Ear
    -1.12
    ovember
    -1.09
    herty
    -1.08
     Kut
    -1.06
    ------------------------------------------------
    -1.05
    dfx
    -1.05
    azy
    -1.04
    POSITIVE LOGITS
     bible
    1.20
    tested
    1.19
    achine
    1.13
    ét
    1.10
    wagen
    1.08
    clinton
    1.07
    science
    1.03
     shells
    1.00
    damage
    0.99
     Nou
    0.99
    Activations Density 0.005%

    No Known Activations