© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 39764
    Prev
    Next
    INDEX
    Explanations

    references to ransomware and its effects on systems and data

    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
    2:0.04
    3:0.06
    4:0.04
    5:0.04
    6:0.04
    7:0.04
    8:0.04
    9:0.07
    10:0.43
    11:0.13
    Negative Logits
    iquette
    -1.71
     etiquette
    -1.66
     Volunte
    -1.54
     Trek
    -1.45
     politic
    -1.44
     canoe
    -1.44
     conscientious
    -1.42
     wiser
    -1.41
     aisle
    -1.40
     Guinness
    -1.38
    POSITIVE LOGITS
     targeting
    1.73
    target
    1.68
     targets
    1.64
    infect
    1.58
     executable
    1.53
    versions
    1.49
     targeted
    1.48
    Pred
    1.46
     attacks
    1.46
    roma
    1.46
    Activations Density 0.047%

    No Known Activations