© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 2549
    Prev
    Next
    INDEX
    Explanations

    references to articles and related materials in writing

    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
    0:0.03
    1:0.02
    2:0.09
    3:0.05
    4:0.06
    5:0.04
    6:0.21
    7:0.08
    8:0.04
    9:0.05
    10:0.15
    11:0.14
    Negative Logits
     stagnation
    -1.65
     Stuff
    -1.52
     Zeit
    -1.51
     cliché
    -1.44
     Condition
    -1.41
     pessim
    -1.41
    CONCLUS
    -1.36
     adaptation
    -1.35
    �
    -1.32
    シャ
    -1.31
    POSITIVE LOGITS
    members
    1.64
    agall
    1.52
    avorite
    1.46
    ecast
    1.44
     swoop
    1.42
    ensis
    1.42
    merce
    1.40
    hang
    1.39
    NECT
    1.38
    votes
    1.38
    Activations Density 0.000%

    No Known Activations