© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28471
    Prev
    Next
    INDEX
    Explanations

    names and titles related to individuals, particularly those associated with significant incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.04
    2:0.05
    3:0.06
    4:0.05
    5:0.05
    6:0.41
    7:0.04
    8:0.04
    9:0.07
    10:0.08
    11:0.05
    Negative Logits
    ══
    -1.58
     pestic
    -1.47
    taboola
    -1.46
    MAP
    -1.43
    Asset
    -1.30
    :{
    -1.26
     MAP
    -1.25
    ADA
    -1.20
    Plugin
    -1.20
    ��
    -1.18
    POSITIVE LOGITS
    otos
    1.67
    ouver
    1.56
    lik
    1.54
    culosis
    1.50
    eus
    1.48
    lycer
    1.45
    isky
    1.40
    ciating
    1.40
    isen
    1.39
    xual
    1.39
    Activations Density 0.008%

    No Known Activations