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. 13799
    Prev
    Next
    INDEX
    Explanations

    phrases related to intense suffering or emotional turmoil

    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
    0:0.04
    1:0.03
    2:0.22
    3:0.05
    4:0.24
    5:0.05
    6:0.03
    7:0.02
    8:0.06
    9:0.10
    10:0.06
    11:0.03
    Negative Logits
    uilding
    -1.39
     ILCS
    -1.28
    uilt
    -1.26
    ilts
    -1.25
     Wealth
    -1.24
     Inher
    -1.24
    services
    -1.23
     Revenue
    -1.21
    oufl
    -1.20
    ticket
    -1.20
    POSITIVE LOGITS
    amine
    1.49
    eness
    1.39
     wounding
    1.36
     mode
    1.36
     laughter
    1.30
    lihood
    1.28
     toxin
    1.27
     bout
    1.26
     ensued
    1.25
     bladder
    1.25
    Activations Density 0.001%

    No Known Activations