© 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. 10-ATT-KK
    11. 10149
    Prev
    Next
    INDEX
    Explanations

    discussions around government regulations and oversight in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.02
    2:0.16
    3:0.15
    4:0.17
    5:0.13
    6:0.04
    7:0.06
    8:0.02
    9:0.09
    10:0.02
    11:0.04
    Negative Logits
     realise
    -3.96
     Whilst
    -3.84
     humour
    -3.82
     apologise
    -3.80
    ´
    -3.63
     organise
    -3.52
     organis
    -3.43
     analyse
    -3.33
     fulfil
    -3.33
     colour
    -3.32
    POSITIVE LOGITS
     --
    3.52
     authorizing
    3.36
     favoring
    3.29
     favorably
    3.06
     antitrust
    3.06
     disproportionately
    2.92
     unconstitutional
    2.92
     federally
    2.89
    --
    2.88
     —
    2.87
    Activations Density 0.689%

    No Known Activations