© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8904
    Prev
    Next
    INDEX
    Explanations

    references to investigations or occurrences related to criminal or missing person cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.02
    2:0.02
    3:0.05
    4:0.04
    5:0.17
    6:0.02
    7:0.03
    8:0.01
    9:0.50
    10:0.02
    11:0.04
    Negative Logits
     portray
    -2.69
     adore
    -2.48
    Reviewer
    -2.37
     despise
    -2.30
     reverence
    -2.24
     derog
    -2.23
    \">
    -2.18
     praise
    -2.16
     Represent
    -2.16
     Saying
    -2.12
    POSITIVE LOGITS
     occurs
    4.53
     occurred
    4.26
     happens
    4.09
     awaits
    4.08
     begins
    4.07
     expires
    4.01
     happened
    3.95
     commenced
    3.89
    pires
    3.87
     arises
    3.83
    Activations Density 0.731%

    No Known Activations