© 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. 2-ATT-KK
    6. 23300
    Prev
    Next
    INDEX
    Explanations

    sentences related to sports teams, events, and discussions

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

    elements of teamwork and collaboration in sports

    oai_token-act-pair · gpt-4o-miniTriggered 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
    0:0.05
    1:0.11
    2:0.04
    3:0.06
    4:0.03
    5:0.05
    6:0.12
    7:0.09
    8:0.05
    9:0.05
    10:0.20
    11:0.09
    Negative Logits
    eming
    -1.31
    itled
    -1.29
     SHARES
    -1.25
    schild
    -1.25
    surprisingly
    -1.25
    reports
    -1.24
    rencies
    -1.24
    utterstock
    -1.22
    wic
    -1.21
    overed
    -1.20
    POSITIVE LOGITS
    )."
    2.12
    .'"
    1.89
     …"
    1.89
    ]."
    1.83
    ..."
    1.78
    ."[
    1.64
    .''
    1.54
    ?'"
    1.53
    }"
    1.52
    '."
    1.50
    Activations Density 0.641%

    No Known Activations