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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 22307
    Prev
    Next
    INDEX
    Explanations

    phrases related to luck and its impact on success or outcomes

    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
    0:0.06
    1:0.03
    2:0.13
    3:0.08
    4:0.09
    5:0.09
    6:0.03
    7:0.03
    8:0.08
    9:0.22
    10:0.08
    11:0.04
    Negative Logits
    ailable
    -1.36
    Downloadha
    -1.32
    ategories
    -1.29
    ategory
    -1.27
    anguage
    -1.22
     Cosponsors
    -1.21
    folios
    -1.21
    rir
    -1.21
    liament
    -1.21
    ujah
    -1.21
    POSITIVE LOGITS
     mortals
    1.28
     camel
    1.26
     Hansen
    1.17
     charms
    1.13
    -->
    1.12
     Chocobo
    1.11
     Elves
    1.09
     miracles
    1.08
     insomnia
    1.08
     Loki
    1.08
    Activations Density 0.006%

    No Known Activations