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. 13962
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal emotions and reflections

    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
    0:0.06
    1:0.02
    2:0.11
    3:0.07
    4:0.02
    5:0.08
    6:0.02
    7:0.06
    8:0.25
    9:0.07
    10:0.11
    11:0.06
    Negative Logits
    wcsstore
    -1.35
    Plugin
    -1.15
     Cosponsors
    -1.14
    MN
    -1.11
     Admission
    -1.02
     ACTIONS
    -1.01
    odynamic
    -1.00
    idth
    -1.00
    xtap
    -1.00
     Used
    -0.99
    POSITIVE LOGITS
     untouched
    1.26
     unfinished
    1.22
     ashes
    1.19
     Ruk
    1.14
     scars
    1.11
     shack
    1.11
     unresolved
    1.10
     charred
    1.10
     shores
    1.09
     laure
    1.08
    Activations Density 0.116%

    No Known Activations