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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 7504
    Prev
    Next
    INDEX
    Explanations

    terms related to reimbursement and compensation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.04
    3:0.05
    4:0.14
    5:0.04
    6:0.03
    7:0.37
    8:0.03
    9:0.03
    10:0.08
    11:0.10
    Negative Logits
    knife
    -1.41
    cone
    -1.35
    vine
    -1.32
    stown
    -1.31
    cade
    -1.29
    pole
    -1.27
    starter
    -1.25
    scape
    -1.24
    wagon
    -1.23
    flower
    -1.21
    POSITIVE LOGITS
     reimburse
    1.90
     reimbursement
    1.78
     refund
    1.77
     reimb
    1.76
     debts
    1.58
     loans
    1.55
     concess
    1.54
     refunds
    1.54
     repay
    1.44
     recomp
    1.42
    Activations Density 0.001%

    No Known Activations