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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 42712
    Prev
    Next
    INDEX
    Explanations

    elements related to financial transactions and significant expenditures

    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
    0:0.03
    1:0.02
    2:0.15
    3:0.12
    4:0.10
    5:0.06
    6:0.03
    7:0.04
    8:0.07
    9:0.10
    10:0.14
    11:0.08
    Negative Logits
     Jagu
    -1.23
     Mush
    -1.20
    hran
    -1.16
     kidn
    -1.15
    lyak
    -1.14
     Phi
    -1.11
     advances
    -1.11
     Griff
    -1.11
     Somers
    -1.10
     conced
    -1.09
    POSITIVE LOGITS
    channelAvailability
    1.63
    cludes
    1.57
     respectively
    1.55
    ategor
    1.42
    cellaneous
    1.37
    etheless
    1.36
    Topic
    1.35
    ibliography
    1.35
    ividually
    1.33
    include
    1.30
    Activations Density 0.566%

    No Known Activations