© 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. 7097
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the effectiveness or perception of treatment outcomes

    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
    1:0.09
    2:0.09
    3:0.08
    4:0.07
    5:0.07
    6:0.08
    7:0.08
    8:0.08
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
    eping
    -3.19
    Root
    -3.19
    eport
    -3.11
    posure
    -2.96
    hered
    -2.96
    Target
    -2.90
    ursed
    -2.77
    reshold
    -2.76
    orgetown
    -2.75
    oused
    -2.72
    POSITIVE LOGITS
     mathematics
    3.33
     mathematic
    3.26
     Mathematics
    3.25
     MET
    3.23
     mathematical
    3.20
     Statistical
    3.08
     Mathemat
    3.06
     unified
    2.95
     math
    2.71
     analytic
    2.69
    Activations Density 0.000%

    No Known Activations