© 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. 3-ATT-KK
    11. 7361
    Prev
    Next
    INDEX
    Explanations

    quantitative metrics and figures related to expectations and goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.05
    2:0.08
    3:0.03
    4:0.03
    5:0.04
    6:0.05
    7:0.05
    8:0.11
    9:0.26
    10:0.07
    11:0.15
    Negative Logits
    INGTON
    -1.51
    BUG
    -1.48
    Appearance
    -1.39
    ourn
    -1.37
    eva
    -1.34
    ghost
    -1.30
    Pokémon
    -1.29
    looking
    -1.28
    PE
    -1.27
     wondered
    -1.26
    POSITIVE LOGITS
     barrier
    1.74
     hurdle
    1.52
     category
    1.50
     limit
    1.46
     designation
    1.45
     gulf
    1.42
     cutoff
    1.36
     criterion
    1.36
     Nay
    1.34
     point
    1.31
    Activations Density 0.015%

    No Known Activations