© 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. 22628
    Prev
    Next
    INDEX
    Explanations

    mentions of technical terms and concepts in business or political contexts

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

    instances of structural definitions and significant occurrences within a text

    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
    0:0.06
    1:0.03
    2:0.09
    3:0.20
    4:0.02
    5:0.10
    6:0.07
    7:0.06
    8:0.05
    9:0.08
    10:0.13
    11:0.06
    Negative Logits
    inas
    -1.26
    obiles
    -1.13
    エル
    -1.06
    oes
    -1.05
    photos
    -1.02
    aneers
    -0.96
    idel
    -0.95
    undreds
    -0.95
    erville
    -0.95
    tted
    -0.94
    POSITIVE LOGITS
     however
    1.24
     moreover
    1.15
    INC
    1.04
     SHALL
    1.02
     furthermore
    1.02
     therefore
    1.01
     GAM
    0.99
     exacerbated
    0.98
    RP
    0.97
    ework
    0.95
    Activations Density 0.183%

    No Known Activations