© 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. 20326
    Prev
    Next
    INDEX
    Explanations

    key phrases related to decision-making and moral implications

    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
    0:0.04
    1:0.04
    2:0.05
    3:0.07
    4:0.13
    5:0.02
    6:0.22
    7:0.17
    8:0.02
    9:0.03
    10:0.03
    11:0.11
    Negative Logits
    Legend
    -2.44
    ngth
    -2.26
     disappeared
    -2.10
    afort
    -2.09
     rust
    -2.09
     demo
    -2.07
    osponsors
    -2.05
    nin
    -2.03
    aunder
    -2.01
     Demo
    -2.01
    POSITIVE LOGITS
     decisions
    5.66
     decision
    5.18
     Decision
    4.52
     choices
    3.70
     judgement
    3.56
     judgment
    3.41
     judgments
    3.34
     deliberations
    3.16
     deliber
    3.08
     deciding
    3.04
    Activations Density 0.170%

    No Known Activations