© 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. 16010
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial amounts and comparisons

    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
    0:0.02
    1:0.04
    2:0.06
    3:0.04
    4:0.11
    5:0.06
    6:0.03
    7:0.08
    8:0.02
    9:0.28
    10:0.04
    11:0.15
    Negative Logits
     disbanded
    -2.65
    Introduced
    -2.60
     participated
    -2.21
    failed
    -2.21
    umbn
    -2.20
    ocard
    -2.15
     apologised
    -2.12
    REDACTED
    -2.07
    displayText
    -2.05
    esm
    -2.00
    POSITIVE LOGITS
     totals
    3.11
     increase
    3.02
     doubling
    3.01
     percentage
    2.92
     averages
    2.92
     staggering
    2.82
     estimate
    2.82
     amount
    2.79
     whopping
    2.78
     equals
    2.75
    Activations Density 0.101%

    No Known Activations