© 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. 12908
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names

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

    terms associated with legal and governmental processes

    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
    0:0.03
    1:0.08
    2:0.12
    3:0.03
    4:0.04
    5:0.09
    6:0.08
    7:0.23
    8:0.09
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
    Downloadha
    -1.32
     depending
    -1.24
     overlap
    -1.24
    depending
    -1.20
     equation
    -1.20
    $.
    -1.19
     respectively
    -1.18
     refres
    -1.18
    paralle
    -1.14
    ngth
    -1.09
    POSITIVE LOGITS
     NEWS
    1.87
     SERVICES
    1.63
     EDITION
    1.54
     REPORT
    1.51
     PRES
    1.48
    IVES
    1.47
    FIELD
    1.47
    MENT
    1.45
    ULL
    1.45
    LET
    1.45
    Activations Density 0.121%

    No Known Activations