© 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. 5-ATT-KK
    11. 41309
    Prev
    Next
    INDEX
    Explanations

    statements of fact or opinions related to morality and ethics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.35
    3:0.08
    4:0.04
    5:0.06
    6:0.03
    7:0.03
    8:0.03
    9:0.07
    10:0.08
    11:0.12
    Negative Logits
    fell
    -1.64
    ahi
    -1.52
    payment
    -1.51
    icter
    -1.50
    ngth
    -1.48
    apsed
    -1.48
    stad
    -1.45
    ayn
    -1.43
    ari
    -1.38
    vir
    -1.38
    POSITIVE LOGITS
     careful
    1.59
     ensured
    1.43
     meticulous
    1.43
     reasoned
    1.43
     tedious
    1.43
     Parables
    1.42
     mindful
    1.42
     eleg
    1.42
     preferably
    1.40
     simpl
    1.40
    Activations Density 0.225%

    No Known Activations