© 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. 10-ATT-KK
    11. 7650
    Prev
    Next
    INDEX
    Explanations

    concepts related to financial withdrawals, particularly from investment accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.21
    2:0.03
    3:0.09
    4:0.04
    5:0.02
    6:0.15
    7:0.12
    8:0.01
    9:0.03
    10:0.07
    11:0.05
    Negative Logits
     Parables
    -2.58
     privileged
    -2.48
     Claud
    -2.46
     Ramsey
    -2.39
     liner
    -2.36
     rooft
    -2.35
    racuse
    -2.31
     Teach
    -2.26
     olig
    -2.22
    Lear
    -2.21
    POSITIVE LOGITS
     withdraw
    6.19
     withdrawal
    6.17
     withdrawn
    5.80
     withdrawing
    5.68
     withdrew
    5.62
     withdrawals
    5.58
    draw
    3.34
     disav
    2.83
     rescind
    2.78
     abst
    2.67
    Activations Density 0.014%

    No Known Activations