© 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. 14712
    Prev
    Next
    INDEX
    Explanations

    financial and political terms like "trust," "tax credit," "bank," "budget," "Commission," and "bill."

    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
    0:0.29
    1:0.04
    2:0.08
    3:0.09
    4:0.03
    5:0.08
    6:0.05
    7:0.03
    8:0.06
    9:0.11
    10:0.07
    11:0.02
    Negative Logits
     conclud
    -2.31
    yss
    -2.00
     acknow
    -1.98
     behavi
    -1.92
     arrang
    -1.89
    iblical
    -1.86
     awa
    -1.85
    ailable
    -1.84
     fundament
    -1.84
    xual
    -1.81
    POSITIVE LOGITS
     mole
    1.71
     DH
    1.56
    caster
    1.51
     Stanton
    1.50
     SS
    1.47
     Stoke
    1.45
     circa
    1.41
     Fr
    1.39
     slumped
    1.39
    gel
    1.37
    Activations Density 0.427%

    No Known Activations