© 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. 8863
    Prev
    Next
    INDEX
    Explanations

    incidents involving injuries or fatalities related to fires or accidents

    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
    2:0.05
    3:0.16
    4:0.25
    5:0.19
    6:0.03
    7:0.05
    8:0.03
    9:0.08
    10:0.03
    11:0.03
    Negative Logits
     organise
    -3.32
    Firstly
    -3.31
    Reviewer
    -3.18
     Mehran
    -3.13
     realise
    -3.11
     organising
    -3.10
     fulfil
    -2.99
    ".[
    -2.89
     emphas
    -2.81
     Whilst
    -2.78
    POSITIVE LOGITS
     Investigators
    3.58
     Saturday
    3.30
     Tuesday
    3.16
     Wednesday
    3.09
     Friday
    3.07
     investigators
    3.06
     Thursday
    3.06
     reported
    3.04
     Monday
    3.02
     paramedics
    2.97
    Activations Density 0.894%

    No Known Activations