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

    Neuronpedia

    Jacobian LensNEW
    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. 41800
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the acceleration or improvement of processes

    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
    1:0.01
    2:0.06
    3:0.07
    4:0.18
    5:0.02
    6:0.04
    7:0.33
    8:0.03
    9:0.03
    10:0.07
    11:0.10
    Negative Logits
    ��
    -1.64
     hostages
    -1.46
    ���
    -1.46
     dummy
    -1.41
     placeholder
    -1.36
     Reserved
    -1.28
    itals
    -1.25
    utherland
    -1.24
    utenant
    -1.24
    empty
    -1.24
    POSITIVE LOGITS
    ogenesis
    1.70
    oS
    1.69
     adoption
    1.64
     turnaround
    1.62
     passage
    1.60
     childbirth
    1.58
     bidding
    1.53
     innovation
    1.53
    paced
    1.52
     deliveries
    1.46
    Activations Density 0.003%

    No Known Activations