© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 39819
    Prev
    Next
    INDEX
    Explanations

    instances of whether events or actions are happening in relation to villains or conflict

    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
    2:0.07
    3:0.25
    4:0.20
    5:0.03
    6:0.04
    7:0.06
    8:0.06
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
    )?
    -2.39
    )</
    -1.97
    "},{"
    -1.94
    ?,
    -1.74
    DragonMagazine
    -1.71
    "?
    -1.71
    .?
    -1.70
    anova
    -1.69
    '?
    -1.64
    rely
    -1.64
    POSITIVE LOGITS
     flooded
    1.88
     arrived
    1.77
     approached
    1.76
     slashed
    1.67
     stormed
    1.64
     rushed
    1.63
    nered
    1.63
     leaked
    1.61
     intervened
    1.50
     stopped
    1.49
    Activations Density 0.057%

    No Known Activations