© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15065
    Prev
    Next
    INDEX
    Explanations

    key terms related to environmental issues and their impacts on society

    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
    1:0.05
    2:0.03
    3:0.04
    4:0.04
    5:0.26
    6:0.04
    7:0.06
    8:0.02
    9:0.08
    10:0.04
    11:0.26
    Negative Logits
     nothing
    -2.42
     without
    -2.33
     worthless
    -2.32
     anytime
    -2.31
     indistinguishable
    -2.27
     indefinitely
    -2.27
     brushed
    -2.24
     nowhere
    -2.22
     refused
    -2.21
     shorthand
    -2.19
    POSITIVE LOGITS
    UAL
    2.53
    role
    2.47
    ADD
    2.40
    MOD
    2.40
     contributes
    2.38
    SourceFile
    2.38
    ;;;;;;;;
    2.35
     Cosponsors
    2.35
    PLAY
    2.35
    plays
    2.34
    Activations Density 0.004%

    No Known Activations