© 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. 22130
    Prev
    Next
    INDEX
    Explanations

    references to socialism and capitalism, along with their associated ideologies and implications

    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
    0:0.04
    1:0.05
    2:0.15
    3:0.08
    4:0.04
    5:0.07
    6:0.03
    7:0.05
    8:0.05
    9:0.27
    10:0.08
    11:0.03
    Negative Logits
    ONY
    -1.49
    IDENT
    -1.45
    pez
    -1.43
    aye
    -1.43
     ABE
    -1.38
    uments
    -1.35
    mallow
    -1.34
    ODY
    -1.33
    York
    -1.33
    oops
    -1.31
    POSITIVE LOGITS
     dystop
    1.47
     flourish
    1.42
     engulf
    1.39
     Mormonism
    1.39
     nihil
    1.34
     mutants
    1.31
     relat
    1.30
     blight
    1.28
     marginal
    1.27
     ideals
    1.27
    Activations Density 0.082%

    No Known Activations