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. 22198
    Prev
    Next
    INDEX
    Explanations

    names of prominent athletes and their associated statistics or achievements

    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
    0:0.05
    1:0.07
    2:0.18
    3:0.08
    4:0.03
    5:0.07
    6:0.04
    7:0.05
    8:0.04
    9:0.23
    10:0.08
    11:0.04
    Negative Logits
     0004
    -1.35
     curriculum
    -1.30
     redistributed
    -1.30
     redes
    -1.28
     curric
    -1.27
    ILY
    -1.20
    hiro
    -1.19
    oppers
    -1.18
    lass
    -1.16
    ridges
    -1.16
    POSITIVE LOGITS
     QB
    1.54
    ESPN
    1.44
    NBA
    1.40
     RB
    1.38
     clutch
    1.33
     NBA
    1.31
    QB
    1.30
     defender
    1.30
     teammate
    1.30
     NFL
    1.28
    Activations Density 0.022%

    No Known Activations