© 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. 35171
    Prev
    Next
    INDEX
    Explanations

    mentions of products and features within technology 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
    0:0.02
    1:0.01
    2:0.07
    3:0.09
    4:0.12
    5:0.03
    6:0.03
    7:0.24
    8:0.03
    9:0.05
    10:0.16
    11:0.08
    Negative Logits
    orian
    -1.61
    matter
    -1.58
    acca
    -1.50
    �
    -1.49
    ruciating
    -1.49
    arge
    -1.47
    aneous
    -1.43
    omsky
    -1.41
    udic
    -1.40
    olkien
    -1.40
    POSITIVE LOGITS
     Brav
    1.59
     franchises
    1.54
     licences
    1.52
     Panda
    1.49
     partnerships
    1.42
     Spice
    1.40
     Valentine
    1.38
     Dame
    1.36
     Clover
    1.35
    vr
    1.35
    Activations Density 0.027%

    No Known Activations