© 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. 14255
    Prev
    Next
    INDEX
    Explanations

    adjectives related to qualities and characteristics, particularly those 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
    0:0.04
    1:0.06
    2:0.24
    3:0.04
    4:0.26
    5:0.05
    6:0.03
    7:0.03
    8:0.05
    9:0.05
    10:0.07
    11:0.03
    Negative Logits
    hillary
    -1.78
    anos
    -1.76
    usra
    -1.65
    DEP
    -1.63
    idel
    -1.62
    ea
    -1.55
    eah
    -1.55
    iane
    -1.53
    spons
    -1.52
    IFA
    -1.48
    POSITIVE LOGITS
    nered
    1.37
    opsis
    1.34
     integer
    1.34
     adaptation
    1.29
     tempered
    1.28
     tract
    1.28
     charm
    1.28
     performing
    1.26
     acoustic
    1.26
     fulfilled
    1.26
    Activations Density 0.051%

    No Known Activations