© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    references to updates and access to content or services

    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
    0:0.01
    1:0.01
    2:0.13
    3:0.16
    4:0.12
    5:0.03
    6:0.07
    7:0.22
    8:0.04
    9:0.05
    10:0.05
    11:0.06
    Negative Logits
    gged
    -1.58
     Lumpur
    -1.48
     inexper
    -1.48
     secondly
    -1.44
    akuya
    -1.43
    wat
    -1.41
    oshenko
    -1.40
    ruary
    -1.39
    $.
    -1.38
     foremost
    -1.37
    POSITIVE LOGITS
    bleacher
    1.48
     archive
    1.43
     athletics
    1.43
    othermal
    1.36
     accessible
    1.32
     Vault
    1.31
     cosmos
    1.30
     limitless
    1.30
     POLITICO
    1.29
     Hive
    1.28
    Activations Density 0.001%

    No Known Activations