© 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. 7654
    Prev
    Next
    INDEX
    Explanations

    mentions of significant events, actions, or outcomes in organizational or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.14
    3:0.32
    4:0.11
    5:0.02
    6:0.02
    7:0.09
    8:0.04
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
    inventoryQuantity
    -1.85
    hov
    -1.74
    cdn
    -1.63
    hovah
    -1.61
    ottesville
    -1.59
    ovo
    -1.59
    eva
    -1.56
    vg
    -1.49
    zees
    -1.48
    ��
    -1.45
    POSITIVE LOGITS
     moot
    1.65
    Later
    1.60
     prematurely
    1.56
     unrecogn
    1.53
     unwitting
    1.51
     accordingly
    1.42
    FL
    1.40
    Notable
    1.37
    pload
    1.36
     subsequent
    1.36
    Activations Density 0.149%

    No Known Activations