© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 15223
    Prev
    Next
    INDEX
    Explanations

    mixed activation of alphabet and symbols indicating the neuron may be looking for a specific language or character set

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.04
    2:0.12
    3:0.05
    4:0.06
    5:0.06
    6:0.07
    7:0.13
    8:0.05
    9:0.05
    10:0.16
    11:0.09
    Negative Logits
     disadvant
    -0.96
     challeng
    -0.73
     imaginative
    -0.72
     Gamble
    -0.70
     undermin
    -0.68
     Lopez
    -0.68
     MDMA
    -0.68
     mathemat
    -0.67
     predec
    -0.67
    luster
    -0.66
    POSITIVE LOGITS
    english
    0.97
    ️
    0.86
    ptoms
    0.83
    heed
    0.83
    jriwal
    0.82
    hari
    0.81
    asury
    0.78
    prev
    0.73
     Requirements
    0.72
     Fixed
    0.72
    Activations Density 0.076%

    No Known Activations