© 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. 12229
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to harboring or nurturing thoughts or feelings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to ambition and questionable actions or affiliations

    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
    0:0.03
    1:0.03
    2:0.10
    3:0.10
    4:0.02
    5:0.03
    6:0.08
    7:0.10
    8:0.11
    9:0.18
    10:0.07
    11:0.10
    Negative Logits
     (£
    -0.98
     reverted
    -0.98
    NBC
    -0.97
     abolished
    -0.97
     revert
    -0.96
    £
    -0.95
     textbooks
    -0.93
     Goff
    -0.92
    Indian
    -0.92
     refund
    -0.92
    POSITIVE LOGITS
     sqor
    1.26
    ngth
    1.20
    覚醒
    1.19
    EStreamFrame
    1.03
     Outer
    1.03
    utic
    1.01
    ukemia
    1.01
    bon
    0.99
    bral
    0.98
    nants
    0.98
    Activations Density 0.002%

    No Known Activations