© 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. 3-ATT-KK
    11. 13101
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions or states accompanied by strong emotional language

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

    references to fan reactions and engagement in various contexts

    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
    0:0.01
    1:0.03
    2:0.10
    3:0.03
    4:0.02
    5:0.06
    6:0.14
    7:0.36
    8:0.04
    9:0.02
    10:0.05
    11:0.07
    Negative Logits
    BIT
    -1.25
     derivative
    -1.25
     dimensional
    -1.22
     mediation
    -1.15
     matrix
    -1.14
     longitudinal
    -1.14
     architectural
    -1.13
     explor
    -1.12
     branching
    -1.11
     explanatory
    -1.10
    POSITIVE LOGITS
    pees
    1.65
    joice
    1.42
     rejoice
    1.35
     subscribed
    1.23
    ustomed
    1.22
    aunders
    1.22
    selves
    1.21
    conservancy
    1.19
    nih
    1.19
    rity
    1.19
    Activations Density 0.035%

    No Known Activations