© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 23090
    Prev
    Next
    INDEX
    Explanations

    contractions and possessives ending in 't

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    negative contractions and expressions of possible outcomes or limitations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.11
    1:0.03
    2:0.13
    3:0.04
    4:0.28
    5:0.05
    6:0.03
    7:0.03
    8:0.11
    9:0.04
    10:0.06
    11:0.03
    Negative Logits
    ccording
    -1.49
    iop
    -1.42
    minus
    -1.35
    田
    -1.29
    rang
    -1.28
    isha
    -1.25
    ilian
    -1.23
    employed
    -1.23
    nikov
    -1.23
    dozen
    -1.23
    POSITIVE LOGITS
     anymore
    1.74
     any
    1.63
     anytime
    1.56
     anything
    1.54
     overw
    1.45
     anywhere
    1.42
     anyone
    1.41
     anybody
    1.35
     ANY
    1.35
    peak
    1.32
    Activations Density 0.020%

    No Known Activations