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. 3-ATT-KK
    6. 8395
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports achievements or milestones, especially concerning hat tricks in games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.03
    2:0.09
    3:0.23
    4:0.02
    5:0.02
    6:0.11
    7:0.13
    8:0.04
    9:0.10
    10:0.07
    11:0.08
    Negative Logits
    ascript
    -1.58
     resid
    -1.13
     nonex
    -1.08
    >>>>
    -1.02
    Iterator
    -1.02
    ��
    -1.01
    vez
    -0.97
     payments
    -0.96
    contract
    -0.96
    msg
    -0.94
    POSITIVE LOGITS
    inki
    1.24
    bash
    1.16
    anamo
    1.14
    mong
    1.04
     Blaster
    1.02
    ndra
    1.01
     Allaah
    1.00
     adorned
    0.99
    さ
    0.98
    andals
    0.97
    Activations Density 0.012%

    No Known Activations