Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3167
    Prev
    Next
    INDEX
    Explanations

    phrases and structures related to obligations, choices, and the concept of paying a price for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.19
    1:0.02
    2:0.20
    3:0.12
    4:0.02
    5:0.09
    6:0.03
    7:0.05
    8:0.04
    9:0.03
    10:0.13
    11:0.02
    Negative Logits
     Dupl
    -2.52
     Delicious
    -2.40
    TPPStreamerBot
    -2.35
    ufact
    -2.30
    Hub
    -2.30
     XY
    -2.27
    ensibly
    -2.26
    Bus
    -2.26
    mable
    -2.23
     innovate
    -2.22
    POSITIVE LOGITS
     coffin
    2.97
     aven
    2.78
    venge
    2.61
     assassinated
    2.55
     slain
    2.50
     mourn
    2.49
     vigil
    2.46
     exorc
    2.46
     condol
    2.44
     Bloody
    2.42
    Activations Density 0.001%

    No Known Activations