© 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. 16187
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evaluation or ranking criteria

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.04
    4:0.08
    5:0.07
    6:0.02
    7:0.04
    8:0.01
    9:0.52
    10:0.01
    11:0.09
    Negative Logits
    disabled
    -2.44
    raped
    -2.40
     wrecked
    -2.27
     died
    -2.25
     losers
    -2.20
     deserted
    -2.17
     raped
    -2.15
     stolen
    -2.15
     dumped
    -2.15
     harmed
    -2.12
    POSITIVE LOGITS
     analyse
    3.96
     analyze
    3.80
     analys
    3.76
     ascertain
    3.68
     analysis
    3.67
     understanding
    3.65
     eluc
    3.61
     decipher
    3.59
     examine
    3.52
     assessment
    3.51
    Activations Density 0.796%

    No Known Activations