© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43020
    Prev
    Next
    INDEX
    Explanations

    numeric data or figures related to statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.04
    1:0.07
    2:0.06
    3:0.07
    4:0.08
    5:0.26
    6:0.06
    7:0.03
    8:0.08
    9:0.10
    10:0.05
    11:0.06
    Negative Logits
    Ctrl
    -1.40
     Guant
    -1.40
    swick
    -1.37
     comprom
    -1.36
    terday
    -1.34
    gets
    -1.30
    apter
    -1.29
    abl
    -1.27
    reon
    -1.26
     gestation
    -1.25
    POSITIVE LOGITS
     undocumented
    1.34
     unused
    1.31
    aji
    1.21
     shin
    1.21
     documenting
    1.21
     ordinary
    1.19
     Kik
    1.19
     joking
    1.17
    miah
    1.17
     Filip
    1.15
    Activations Density 0.000%

    No Known Activations