© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 3770
    Prev
    Next
    INDEX
    Explanations

    phrases related to social security and its impact on taxation and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.03
    2:0.06
    3:0.23
    4:0.03
    5:0.11
    6:0.02
    7:0.07
    8:0.05
    9:0.01
    10:0.23
    11:0.04
    Negative Logits
     humour
    -2.68
    nesday
    -2.25
    interstitial
    -2.19
     colourful
    -2.12
     coloured
    -2.11
     enqu
    -2.01
     rumours
    -1.93
     reply
    -1.92
     councillor
    -1.84
     kindly
    -1.84
    POSITIVE LOGITS
     trillions
    2.37
     protections
    2.28
     budgets
    2.24
    —
    2.21
     taxes
    2.19
     premiums
    2.18
     Medicare
    2.18
    —-
    2.15
     ObamaCare
    2.15
     drastically
    2.10
    Activations Density 0.469%

    No Known Activations