© 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. 2-ATT-KK
    11. 15615
    Prev
    Next
    INDEX
    Explanations

    adjectives decribing things with a negative connotation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.01
    2:0.05
    3:0.15
    4:0.07
    5:0.06
    6:0.03
    7:0.09
    8:0.05
    9:0.06
    10:0.17
    11:0.09
    Negative Logits
    ritz
    -1.00
    EngineDebug
    -0.96
    anced
    -0.95
    ijn
    -0.94
    rique
    -0.92
    ouston
    -0.92
    uction
    -0.91
    pathy
    -0.90
     unfocusedRange
    -0.90
    steel
    -0.89
    POSITIVE LOGITS
     imaginable
    1.82
     EVER
    1.56
     ever
    1.46
     besides
    1.27
     Ever
    1.21
    ever
    1.19
    Ever
    1.18
     conceivable
    1.14
    \":
    1.05
    soever
    0.98
    Activations Density 0.441%

    No Known Activations