© 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. 3-ATT-KK
    11. 9340
    Prev
    Next
    INDEX
    Explanations

    statistical relationships and impacts related to health and social issues

    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
    0:0.02
    1:0.05
    2:0.05
    3:0.02
    4:0.03
    5:0.16
    6:0.05
    7:0.06
    8:0.05
    9:0.04
    10:0.06
    11:0.34
    Negative Logits
     relent
    -1.53
     imprint
    -1.51
     timet
    -1.48
     archives
    -1.48
     fi
    -1.47
     precedent
    -1.45
     artist
    -1.37
     rein
    -1.36
    ��
    -1.36
     bookmark
    -1.32
    POSITIVE LOGITS
     polled
    2.07
     surveyed
    2.04
    pees
    1.96
    total
    1.82
     excluding
    1.67
     Including
    1.66
     respondents
    1.66
     Dow
    1.66
     rated
    1.65
    excluding
    1.63
    Activations Density 0.199%

    No Known Activations