© 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. 10-ATT-KK
    11. 9630
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical violence and harm in incidents

    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
    0:0.07
    1:0.05
    2:0.06
    3:0.08
    4:0.22
    5:0.10
    6:0.05
    7:0.09
    8:0.03
    9:0.12
    10:0.04
    11:0.04
    Negative Logits
     Parables
    -2.83
    irable
    -2.75
    vertisement
    -2.74
     enrich
    -2.73
    folios
    -2.70
     incorporation
    -2.67
    iosyncr
    -2.66
     favorable
    -2.64
     esche
    -2.62
    arcity
    -2.58
    POSITIVE LOGITS
     screaming
    4.43
     screamed
    4.36
     yelling
    4.34
     yelled
    4.30
     scared
    4.11
     crying
    4.07
     screams
    4.01
     scream
    3.86
     panicked
    3.84
     shouting
    3.84
    Activations Density 0.432%

    No Known Activations