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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44051
    Prev
    Next
    INDEX
    Explanations

    words indicating capability or potential actions

    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
    2:0.09
    3:0.13
    4:0.08
    5:0.03
    6:0.32
    7:0.09
    8:0.04
    9:0.02
    10:0.06
    11:0.05
    Negative Logits
     Rebellion
    -1.44
     throne
    -1.29
    Bet
    -1.23
    raq
    -1.23
     wagon
    -1.22
     cruiser
    -1.18
     AMA
    -1.15
     Jericho
    -1.15
    activation
    -1.12
     simulator
    -1.12
    POSITIVE LOGITS
    ォ
    1.49
    hemat
    1.47
    vantage
    1.47
    ザ
    1.46
    anned
    1.45
    ーク
    1.45
    krit
    1.44
    ��
    1.43
    ostic
    1.42
    �
    1.42
    Activations Density 0.028%

    No Known Activations