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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42824
    Prev
    Next
    INDEX
    Explanations

    expressions of hope or intention regarding personal or team achievements

    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
    0:0.01
    1:0.01
    2:0.25
    3:0.25
    4:0.07
    5:0.04
    6:0.04
    7:0.06
    8:0.06
    9:0.07
    10:0.08
    11:0.03
    Negative Logits
     Defendants
    -1.90
    .""
    -1.78
    .")
    -1.73
    )."
    -1.53
     disturbances
    -1.52
     intervening
    -1.52
    ankind
    -1.48
    ."[
    -1.46
     therein
    -1.44
     [*
    -1.43
    POSITIVE LOGITS
    channelAvailability
    2.20
     sqor
    1.89
    ール
    1.74
    052
    1.72
    lov
    1.53
    ティ
    1.52
    ui
    1.52
    iland
    1.48
    �
    1.47
    ��
    1.46
    Activations Density 0.017%

    No Known Activations