© 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. 9-ATT-KK
    11. 5390
    Prev
    Next
    INDEX
    Explanations

    instances of theft or burglary-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.08
    3:0.14
    4:0.03
    5:0.32
    6:0.02
    7:0.06
    8:0.04
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
     arson
    -3.69
     massacre
    -3.67
     abuser
    -3.60
     Massacre
    -3.47
    iasco
    -3.46
     Terror
    -3.37
     menace
    -3.35
     bullies
    -3.30
     terrorist
    -3.29
     murderous
    -3.27
    POSITIVE LOGITS
     NIH
    3.12
    ftime
    2.89
    Studio
    2.73
     DVDs
    2.65
     studios
    2.59
    Music
    2.44
    ellen
    2.44
    STEM
    2.40
     programmes
    2.38
    Science
    2.38
    Activations Density 0.068%

    No Known Activations