© 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. 3-ATT-KK
    11. 11919
    Prev
    Next
    INDEX
    Explanations

    details about a specific location or setting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    indicators of emotional intensity or expressions of strong feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.10
    2:0.04
    3:0.02
    4:0.05
    5:0.21
    6:0.04
    7:0.04
    8:0.06
    9:0.03
    10:0.10
    11:0.03
    Negative Logits
    版
    -1.77
    ppers
    -1.75
     Racer
    -1.62
     accelerator
    -1.59
    ビ
    -1.55
     racer
    -1.54
     crates
    -1.50
     scanners
    -1.47
     sprites
    -1.46
    cade
    -1.46
    POSITIVE LOGITS
    answer
    1.86
    atern
    1.86
    arent
    1.83
    subject
    1.70
    aternal
    1.67
    venge
    1.67
    ndum
    1.63
    icip
    1.60
    emphasis
    1.58
    ynski
    1.58
    Activations Density 0.191%

    No Known Activations