© 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. 12653
    Prev
    Next
    INDEX
    Explanations

    phrases related to remaining portions or continuations of text

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

    phrases indicating the duration or remaining time of events or situations

    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
    1:0.02
    2:0.06
    3:0.27
    4:0.01
    5:0.02
    6:0.09
    7:0.07
    8:0.04
    9:0.04
    10:0.07
    11:0.24
    Negative Logits
     Tracker
    -1.10
     Dating
    -1.08
     precursor
    -1.05
     Omaha
    -1.03
     Leadership
    -1.03
     mirrored
    -1.01
     conducive
    -1.01
     colle
    -1.01
     enough
    -1.01
    acus
    -1.01
    POSITIVE LOGITS
    imester
    1.36
    igon
    1.25
    aska
    1.21
    iatus
    1.20
    hour
    1.18
    hash
    1.17
    ietal
    1.15
    ğ
    1.15
    ardon
    1.14
    в
    1.13
    Activations Density 0.003%

    No Known Activations