© 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. 43452
    Prev
    Next
    INDEX
    Explanations

    mention of major technology and automobile companies

    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
    0:0.14
    1:0.02
    2:0.13
    3:0.04
    4:0.03
    5:0.04
    6:0.07
    7:0.01
    8:0.16
    9:0.07
    10:0.13
    11:0.11
    Negative Logits
    emetery
    -1.69
    owship
    -1.68
    zee
    -1.67
    indu
    -1.59
    hing
    -1.56
    irable
    -1.53
    incarn
    -1.52
    :]
    -1.52
    istence
    -1.50
    urate
    -1.48
    POSITIVE LOGITS
    etc
    2.01
     Asus
    1.91
     Motorola
    1.78
     Alc
    1.75
     Huawei
    1.74
     etc
    1.73
     Samsung
    1.73
     BlackBerry
    1.70
     Tel
    1.68
     Gmail
    1.65
    Activations Density 0.032%

    No Known Activations