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. 8445
    Prev
    Next
    INDEX
    Explanations

    terms related to sports championships and defensive tactics

    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
    0:0.02
    1:0.03
    2:0.10
    3:0.13
    4:0.02
    5:0.04
    6:0.09
    7:0.16
    8:0.11
    9:0.09
    10:0.06
    11:0.09
    Negative Logits
    yip
    -1.36
    ��
    -1.27
     haircut
    -1.27
    iasco
    -1.19
     Bought
    -1.18
    umn
    -1.11
    iru
    -1.10
    ulhu
    -1.08
    orah
    -1.07
     footnote
    -1.04
    POSITIVE LOGITS
     flank
    1.22
     Champions
    1.13
    hots
    1.13
     fronts
    1.11
     Defensive
    1.06
     midfield
    1.03
    arter
    1.02
     Rookie
    1.01
     cylinders
    0.98
     MVP
    0.98
    Activations Density 0.007%

    No Known Activations