© 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. 42616
    Prev
    Next
    INDEX
    Explanations

    keywords related to governance and public accountability

    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
    1:0.02
    2:0.09
    3:0.10
    4:0.41
    5:0.03
    6:0.06
    7:0.06
    8:0.03
    9:0.04
    10:0.05
    11:0.03
    Negative Logits
    anything
    -1.42
    �
    -1.40
     Cursed
    -1.39
     Anon
    -1.36
    alloween
    -1.36
    ertodd
    -1.35
    、
    -1.35
     Cabin
    -1.35
    password
    -1.33
    て
    -1.31
    POSITIVE LOGITS
     nor
    1.99
    "]=>
    1.84
    aires
    1.66
    unts
    1.49
    phe
    1.48
    irmed
    1.45
    ase
    1.45
    anned
    1.43
    ople
    1.42
    othe
    1.38
    Activations Density 0.070%

    No Known Activations