© 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. 28495
    Prev
    Next
    INDEX
    Explanations

    dates and postings in a timeline context

    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
    0:0.03
    1:0.01
    2:0.09
    3:0.06
    4:0.11
    5:0.04
    6:0.20
    7:0.11
    8:0.04
    9:0.06
    10:0.09
    11:0.10
    Negative Logits
     settled
    -1.24
    vey
    -1.19
    orney
    -1.07
    redo
    -1.05
    liest
    -1.05
    cca
    -1.03
     landfall
    -1.02
     sue
    -1.01
     settling
    -1.01
     suing
    -1.01
    POSITIVE LOGITS
    mortem
    1.20
    strength
    1.17
    エル
    1.16
    thora
    1.16
     throats
    1.15
    agram
    1.09
    roc
    1.07
    atro
    1.05
    BuyableInstoreAndOnline
    1.04
     wrists
    1.03
    Activations Density 0.003%

    No Known Activations