© 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. 5-ATT-KK
    11. 45845
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opinions or assessments

    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
    0:0.02
    1:0.00
    2:0.18
    3:0.08
    4:0.20
    5:0.02
    6:0.05
    7:0.08
    8:0.09
    9:0.05
    10:0.05
    11:0.11
    Negative Logits
     respectively
    -1.62
     denotes
    -1.50
     preferably
    -1.46
    ��
    -1.42
     contingent
    -1.41
    ={
    -1.38
     kindred
    -1.35
     synonymous
    -1.33
     shalt
    -1.30
    unique
    -1.29
    POSITIVE LOGITS
     anymore
    2.24
     nor
    1.79
    nor
    1.71
    sid
    1.50
    due
    1.43
     Nor
    1.37
    yet
    1.36
    Nonetheless
    1.35
    rons
    1.34
    erm
    1.29
    Activations Density 0.012%

    No Known Activations