© 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 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. 28268
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with scores or performances

    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
    0:0.13
    1:0.09
    2:0.10
    3:0.06
    4:0.04
    5:0.10
    6:0.04
    7:0.01
    8:0.12
    9:0.07
    10:0.05
    11:0.12
    Negative Logits
    orney
    -1.60
    ographies
    -1.59
     Seym
    -1.57
     ®
    -1.54
     Authors
    -1.46
     Writing
    -1.45
     distinguishing
    -1.43
    orget
    -1.41
     SOFTWARE
    -1.40
    eaturing
    -1.39
    POSITIVE LOGITS
    alore
    1.63
    elope
    1.40
    altern
    1.37
    mates
    1.34
    Phys
    1.33
    move
    1.32
     carc
    1.32
    morrow
    1.31
    Talk
    1.29
    Bed
    1.29
    Activations Density 0.002%

    No Known Activations