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. 44278
    Prev
    Next
    INDEX
    Explanations

    references to legislative and governmental committees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.02
    2:0.06
    3:0.05
    4:0.04
    5:0.03
    6:0.41
    7:0.03
    8:0.03
    9:0.05
    10:0.07
    11:0.14
    Negative Logits
    idious
    -1.65
    endi
    -1.39
    otti
    -1.26
     princip
    -1.24
    utral
    -1.24
    henko
    -1.24
    itive
    -1.22
    isner
    -1.19
     clauses
    -1.19
    achev
    -1.18
    POSITIVE LOGITS
    alogue
    1.37
    Lua
    1.30
    Times
    1.27
     Emirates
    1.25
     earthqu
    1.22
     Nou
    1.22
     Yon
    1.22
    RAFT
    1.16
    addon
    1.14
     RG
    1.13
    Activations Density 0.009%

    No Known Activations