© 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. 2-ATT-KK
    11. 13535
    Prev
    Next
    INDEX
    Explanations

    phrases related to news events or incidents, particularly focusing on alarming situations or statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.03
    2:0.04
    3:0.11
    4:0.02
    5:0.10
    6:0.05
    7:0.12
    8:0.10
    9:0.03
    10:0.18
    11:0.10
    Negative Logits
     moreover
    -0.82
     furthermore
    -0.73
    ilities
    -0.72
    imore
    -0.72
     meanwhile
    -0.69
     GOODMAN
    -0.69
    イト
    -0.68
     disproportion
    -0.67
    ETF
    -0.67
     Wem
    -0.66
    POSITIVE LOGITS
    liest
    0.68
    pires
    0.67
    Nov
    0.66
     progresses
    0.65
    arten
    0.63
     spoiled
    0.63
    haps
    0.62
     unfolds
    0.62
    cised
    0.62
    Pod
    0.62
    Activations Density 0.282%

    No Known Activations