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. 8506
    Prev
    Next
    INDEX
    Explanations

    quantitative measures related to frequency, amount, and units of consumption

    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
    0:0.05
    1:0.02
    2:0.22
    3:0.22
    4:0.03
    5:0.02
    6:0.04
    7:0.05
    8:0.10
    9:0.03
    10:0.08
    11:0.08
    Negative Logits
     strains
    -1.23
     Tanks
    -1.19
    ibaba
    -1.14
    amaz
    -1.06
    �
    -1.06
    soDeliveryDate
    -1.06
    �
    -1.05
    behind
    -1.05
     prototypes
    -1.05
     surprises
    -1.05
    POSITIVE LOGITS
    imeter
    1.78
    otaur
    1.31
    reau
    1.29
    idy
    1.26
    etric
    1.19
    idium
    1.18
    aration
    1.14
    urdue
    1.12
    ossession
    1.09
     squared
    1.09
    Activations Density 0.016%

    No Known Activations