© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22047
    Prev
    Next
    INDEX
    Explanations

    terms related to sales and financial performance

    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
    0:0.04
    1:0.09
    2:0.06
    3:0.08
    4:0.03
    5:0.07
    6:0.04
    7:0.08
    8:0.07
    9:0.26
    10:0.10
    11:0.04
    Negative Logits
     recess
    -1.60
    orgetown
    -1.41
     tom
    -1.32
    eus
    -1.32
    �
    -1.27
    ointed
    -1.26
    olog
    -1.25
    ican
    -1.24
     Oss
    -1.24
     advers
    -1.24
    POSITIVE LOGITS
     sales
    1.72
     buyers
    1.64
     shortages
    1.52
    Sales
    1.52
     profits
    1.50
     profitability
    1.49
     distributors
    1.47
     prices
    1.46
     revenue
    1.46
     Prices
    1.45
    Activations Density 0.029%

    No Known Activations