© 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. 5-ATT-KK
    6. 19059
    Prev
    Next
    INDEX
    Explanations

    references to time periods and transitions associated with events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.15
    3:0.04
    4:0.10
    5:0.02
    6:0.10
    7:0.07
    8:0.06
    9:0.04
    10:0.05
    11:0.09
    Negative Logits
     Lost
    -1.50
    #$
    -1.44
    album
    -1.43
    AAAA
    -1.43
     Really
    -1.38
     Disco
    -1.36
     Balls
    -1.33
     dumps
    -1.32
    umped
    -1.30
    opathy
    -1.29
    POSITIVE LOGITS
    anwhile
    1.67
     conclud
    1.57
    terday
    1.50
     observe
    1.49
    ouver
    1.48
    heastern
    1.47
     constitute
    1.45
    aturday
    1.45
    everal
    1.44
    imester
    1.42
    Activations Density 0.001%

    No Known Activations