© 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 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. 44899
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential danger or threats

    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
    0:0.09
    1:0.34
    2:0.02
    3:0.08
    4:0.02
    5:0.17
    6:0.01
    7:0.01
    8:0.04
    9:0.09
    10:0.04
    11:0.02
    Negative Logits
     penned
    -1.55
    ograp
    -1.48
    reenshots
    -1.42
    claimed
    -1.41
    reviewed
    -1.38
    lein
    -1.38
     NFC
    -1.37
     ↑
    -1.37
     PU
    -1.35
    れ
    -1.35
    POSITIVE LOGITS
    ..."
    2.44
     fools
    1.91
     …"
    1.72
     traged
    1.67
    ..."
    1.64
     millenn
    1.64
     strugg
    1.64
    ________________
    1.61
    "}],"
    1.61
    ��
    1.58
    Activations Density 0.446%

    No Known Activations