© 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. 11811
    Prev
    Next
    INDEX
    Explanations

    details related to crime incidents and investigations

    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
    0:0.03
    1:0.04
    2:0.12
    3:0.05
    4:0.16
    5:0.09
    6:0.07
    7:0.14
    8:0.06
    9:0.04
    10:0.05
    11:0.09
    Negative Logits
    igree
    -2.45
     ageing
    -2.42
    irements
    -2.37
    inding
    -2.24
    urion
    -2.23
    bably
    -2.23
    ingen
    -2.21
    elong
    -2.18
     discont
    -2.18
    acca
    -2.17
    POSITIVE LOGITS
    Police
    4.08
    Investigators
    3.62
    Detect
    3.53
    Officers
    3.51
    Authorities
    3.47
     Police
    3.46
     detectives
    3.31
    Neigh
    3.31
     Investigators
    3.07
    police
    3.04
    Activations Density 0.141%

    No Known Activations