© 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. 5-ATT-KK
    11. 29613
    Prev
    Next
    INDEX
    Explanations

    descriptions of things that are assessed positively or negatively

    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
    2:0.12
    3:0.09
    4:0.13
    5:0.02
    6:0.31
    7:0.10
    8:0.04
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
    Reviewed
    -1.86
    soever
    -1.80
    anamo
    -1.65
     destro
    -1.53
    NRS
    -1.53
    anship
    -1.43
    ngth
    -1.43
    doms
    -1.41
    owship
    -1.40
     conduc
    -1.39
    POSITIVE LOGITS
    fuck
    1.31
     coincidence
    1.27
    ummy
    1.27
    gery
    1.26
     anomaly
    1.26
     yarn
    1.26
     Rough
    1.21
     approximation
    1.18
    hole
    1.18
    pants
    1.17
    Activations Density 0.024%

    No Known Activations