© 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. 9-ATT-KK
    11. 19372
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of numbers or quantity-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.12
    2:0.09
    3:0.06
    4:0.05
    5:0.04
    6:0.17
    7:0.03
    8:0.03
    9:0.25
    10:0.03
    11:0.01
    Negative Logits
     Lau
    -4.08
    aeus
    -3.76
     Cohen
    -3.55
     Tau
    -3.47
     Venus
    -3.46
     lace
    -3.42
     Block
    -3.35
     Peck
    -3.28
    Tag
    -3.26
     Blockchain
    -3.23
    POSITIVE LOGITS
    Reason
    6.74
     Reason
    5.86
    reason
    5.64
    rational
    5.34
     rational
    4.92
     Rational
    4.78
     justification
    4.66
     rationality
    4.55
     reason
    4.20
    asonable
    4.18
    Activations Density 0.005%

    No Known Activations