Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22246
    Prev
    Next
    INDEX
    Explanations

    expressions related to feelings of discomfort or unease

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.04
    1:0.03
    2:0.22
    3:0.05
    4:0.26
    5:0.04
    6:0.02
    7:0.03
    8:0.09
    9:0.09
    10:0.05
    11:0.03
    Negative Logits
    ardless
    -1.43
     Lich
    -1.42
     Aff
    -1.27
     Tsukuyomi
    -1.24
    hetical
    -1.21
     Kore
    -1.21
    hai
    -1.20
     Ess
    -1.18
     Earthquake
    -1.18
     affinity
    -1.17
    POSITIVE LOGITS
    itiveness
    1.60
    ewater
    1.48
     Alto
    1.35
    beck
    1.33
    bour
    1.33
    ths
    1.32
    opers
    1.30
    Ã
    1.30
     frogs
    1.20
    nir
    1.20
    Activations Density 0.000%

    No Known Activations