© 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. 12961
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluation or analysis, especially with terms like "make sense," "agree between," and "match the fantasy."

    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
    0:0.14
    1:0.03
    2:0.05
    3:0.05
    4:0.06
    5:0.08
    6:0.05
    7:0.11
    8:0.04
    9:0.06
    10:0.19
    11:0.09
    Negative Logits
     eleph
    -1.04
    accompanied
    -0.90
    soDeliveryDate
    -0.89
     assorted
    -0.81
     Complex
    -0.76
     redes
    -0.76
     newcom
    -0.76
     gist
    -0.76
    anwhile
    -0.75
    endix
    -0.74
    POSITIVE LOGITS
     nor
    2.04
     anymore
    1.89
    yet
    1.47
    nor
    1.35
     yet
    1.19
     whatsoever
    1.03
    Nor
    1.00
     Nor
    1.00
     necessarily
    0.99
     unless
    0.97
    Activations Density 0.502%

    No Known Activations