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. 14059
    Prev
    Next
    INDEX
    Explanations

    phrases related to baseball equipment and interactions between individuals in a baseball context

    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
    0:0.03
    1:0.09
    2:0.13
    3:0.06
    4:0.09
    5:0.15
    6:0.09
    7:0.03
    8:0.08
    9:0.14
    10:0.04
    11:0.02
    Negative Logits
     🙂
    -1.44
     ;)
    -1.41
     shitty
    -1.40
    abbage
    -1.30
    iflower
    -1.29
     nerds
    -1.28
     blogging
    -1.28
    atom
    -1.28
     Boko
    -1.27
     Discord
    -1.24
    POSITIVE LOGITS
    Wilson
    1.52
    Senior
    1.51
    Said
    1.41
     trailed
    1.41
    QB
    1.37
     Kinn
    1.37
    pex
    1.34
     Collins
    1.33
     Rodgers
    1.32
    Anderson
    1.29
    Activations Density 0.011%

    No Known Activations