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. 7510
    Prev
    Next
    INDEX
    Explanations

    financial transactions related to player transfers in sports

    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
    0:0.03
    1:0.02
    2:0.06
    3:0.16
    4:0.05
    5:0.07
    6:0.02
    7:0.06
    8:0.07
    9:0.09
    10:0.18
    11:0.14
    Negative Logits
    paren
    -1.44
    Narr
    -1.36
    Values
    -1.34
    notation
    -1.31
    inant
    -1.26
    ..."
    -1.22
     Libraries
    -1.20
    opoly
    -1.18
    Except
    -1.17
    cery
    -1.16
    POSITIVE LOGITS
     controvers
    1.36
     hopes
    1.33
     campaigners
    1.28
     departing
    1.28
     organisers
    1.24
     plans
    1.22
     2018
    1.20
     keen
    1.18
     inher
    1.18
     revamped
    1.17
    Activations Density 0.278%

    No Known Activations