© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14749
    Prev
    Next
    INDEX
    Explanations

    references to specific television and film roles, particularly those involving popular characters and actors

    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
    0:0.05
    1:0.02
    2:0.03
    3:0.05
    4:0.09
    5:0.18
    6:0.03
    7:0.05
    8:0.04
    9:0.30
    10:0.03
    11:0.08
    Negative Logits
    ══
    -2.89
    Their
    -2.84
     exceeds
    -2.81
    �
    -2.68
    smanship
    -2.59
    They
    -2.54
     exceed
    -2.51
    rehens
    -2.50
     THEY
    -2.47
     THEIR
    -2.44
    POSITIVE LOGITS
     narrator
    3.15
     antagonist
    2.57
    agonist
    2.53
    roo
    2.49
     Guest
    2.49
    bane
    2.47
    angelo
    2.42
    asher
    2.40
     villain
    2.40
     aboard
    2.39
    Activations Density 0.081%

    No Known Activations