© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43424
    Prev
    Next
    INDEX
    Explanations

    entities and companies involved in financial or corporate activities

    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
    2:0.17
    3:0.09
    4:0.06
    5:0.04
    6:0.07
    7:0.05
    8:0.12
    9:0.05
    10:0.13
    11:0.12
    Negative Logits
     quo
    -1.70
     bleed
    -1.51
     plaque
    -1.44
    respective
    -1.43
     cycle
    -1.43
    stra
    -1.42
    isations
    -1.40
     sticker
    -1.35
     inconsistency
    -1.34
     envelope
    -1.32
    POSITIVE LOGITS
    etheless
    1.79
    Catal
    1.63
    soDeliveryDate
    1.57
     Its
    1.37
     conducts
    1.33
    quickShipAvailable
    1.30
    ongyang
    1.26
     ⓘ
    1.26
    asus
    1.25
     MOR
    1.24
    Activations Density 0.078%

    No Known Activations