© 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. 5-ATT-KK
    6. 42933
    Prev
    Next
    INDEX
    Explanations

    words associated with repugnance or negative sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.04
    3:0.06
    4:0.05
    5:0.04
    6:0.44
    7:0.04
    8:0.05
    9:0.07
    10:0.06
    11:0.04
    Negative Logits
    UFF
    -1.30
     womb
    -1.29
    nexus
    -1.25
     裏�
    -1.17
    Spider
    -1.16
     suburbs
    -1.16
    hole
    -1.16
     countryside
    -1.10
     Skydragon
    -1.10
     landscapes
    -1.08
    POSITIVE LOGITS
    ascript
    2.22
    ciating
    1.82
    ciation
    1.64
     sacrific
    1.52
    ruary
    1.48
     sidx
    1.47
    lishes
    1.43
    ctory
    1.40
    bably
    1.38
    nyder
    1.36
    Activations Density 0.002%

    No Known Activations