© 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. 44485
    Prev
    Next
    INDEX
    Explanations

    negative or cautionary phrases and symbols related to computer security or system restrictions

    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
    0:0.15
    1:0.09
    2:0.06
    3:0.05
    4:0.03
    5:0.19
    6:0.04
    7:0.03
    8:0.14
    9:0.07
    10:0.06
    11:0.06
    Negative Logits
     GOODMAN
    -1.67
     recording
    -1.67
     reckoning
    -1.54
     recorder
    -1.53
     interpre
    -1.51
     regard
    -1.51
     scen
    -1.50
     Architects
    -1.44
     Soldiers
    -1.43
    Reviewer
    -1.41
    POSITIVE LOGITS
    egg
    2.38
    gravity
    2.14
    Tag
    2.11
    input
    2.08
    armor
    2.08
    License
    1.99
    contact
    1.99
    drug
    1.98
    your
    1.94
    Url
    1.94
    Activations Density 0.002%

    No Known Activations