© 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. 9-ATT-KK
    11. 412
    Prev
    Next
    INDEX
    Explanations

    references to escape and related actions in the context of crime and law enforcement

    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
    0:0.06
    1:0.02
    2:0.42
    3:0.06
    4:0.02
    5:0.06
    6:0.05
    7:0.08
    8:0.04
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
     Cosponsors
    -2.92
     billing
    -2.66
    eatures
    -2.60
     consultations
    -2.57
    Measure
    -2.53
     topical
    -2.52
     Shea
    -2.48
     Dates
    -2.47
    ritic
    -2.40
    ointment
    -2.39
    POSITIVE LOGITS
     escape
    6.90
     escapes
    6.19
     escaping
    6.18
     escaped
    5.55
     fleeing
    5.52
     Escape
    5.50
     fug
    5.15
    escape
    5.10
     flee
    5.03
     fugitive
    4.56
    Activations Density 0.114%

    No Known Activations