© 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. 20877
    Prev
    Next
    INDEX
    Explanations

    phrases related to exposure and its effects

    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
    0:0.15
    1:0.12
    2:0.05
    3:0.06
    4:0.09
    5:0.03
    6:0.07
    7:0.21
    8:0.02
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
     Asylum
    -2.57
    assian
    -2.40
    REAM
    -2.19
    ctuary
    -2.18
     Empty
    -2.15
    rompt
    -2.15
    ordering
    -2.14
     サ
    -2.13
     Crescent
    -2.12
     Hels
    -2.11
    POSITIVE LOGITS
     exposures
    4.11
     exposure
    3.64
     Exposure
    3.60
     exposed
    3.18
     neurot
    2.94
     expose
    2.75
     benz
    2.73
     susceptibility
    2.65
    posure
    2.64
    bestos
    2.63
    Activations Density 0.015%

    No Known Activations