© 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. 37789
    Prev
    Next
    INDEX
    Explanations

    phrases related to danger and risk

    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
    2:0.15
    3:0.08
    4:0.21
    5:0.03
    6:0.03
    7:0.14
    8:0.05
    9:0.04
    10:0.12
    11:0.08
    Negative Logits
    igne
    -1.35
     conducts
    -1.30
    lav
    -1.26
     approves
    -1.25
     vetoed
    -1.22
    deck
    -1.21
     convened
    -1.21
    olution
    -1.20
    oplan
    -1.19
     headquartered
    -1.19
    POSITIVE LOGITS
    etimes
    1.62
    selves
    1.51
    die
    1.44
    killers
    1.34
    ntil
    1.33
    %.
    1.31
    ________________
    1.29
    %;
    1.29
    isen
    1.27
     Including
    1.26
    Activations Density 0.002%

    No Known Activations