© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23129
    Prev
    Next
    INDEX
    Explanations

    phrases related to intense emotional experiences or acute physical conditions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    occurrences of the word "suffocate" and related terms signaling distress or strain

    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
    0:0.05
    1:0.03
    2:0.18
    3:0.06
    4:0.23
    5:0.03
    6:0.03
    7:0.03
    8:0.12
    9:0.11
    10:0.05
    11:0.03
    Negative Logits
    ��
    -1.60
     Archdemon
    -1.20
     Mehran
    -1.20
    ongyang
    -1.19
     Logged
    -1.17
    version
    -1.16
     Sparrow
    -1.15
     preferential
    -1.15
     profiling
    -1.15
    TIT
    -1.14
    POSITIVE LOGITS
     wounds
    1.36
     suff
    1.31
     blows
    1.30
    iscons
    1.29
    amac
    1.21
    eez
    1.19
    ptoms
    1.17
     breathe
    1.17
    icia
    1.16
     cries
    1.14
    Activations Density 0.002%

    No Known Activations