© 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. 9-ATT-KK
    6. 3335
    Prev
    Next
    INDEX
    Explanations

    phrases indicating public approval or disapproval, particularly in political contexts

    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
    0:0.13
    1:0.05
    2:0.13
    3:0.05
    4:0.09
    5:0.09
    6:0.09
    7:0.09
    8:0.04
    9:0.10
    10:0.05
    11:0.03
    Negative Logits
     Sparks
    -2.55
    wake
    -2.31
     deadlines
    -2.28
     CODE
    -2.28
     ROCK
    -2.27
    inders
    -2.26
     Saga
    -2.24
    Volume
    -2.20
     Drum
    -2.17
     Crack
    -2.17
    POSITIVE LOGITS
     unfavorable
    3.67
     favorable
    3.27
    pleasant
    3.11
     favourable
    3.04
     favorably
    2.98
    neutral
    2.95
    utral
    2.87
     neutral
    2.75
    appro
    2.56
     flattering
    2.56
    Activations Density 0.002%

    No Known Activations