© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-ATT-KK
    11. 23335
    Prev
    Next
    INDEX
    Explanations

    keywords related to events or occurrences, potentially focusing on the sequence of events

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

    expressions of change or transitioning situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.11
    3:0.21
    4:0.08
    5:0.06
    6:0.06
    7:0.02
    8:0.06
    9:0.19
    10:0.07
    11:0.03
    Negative Logits
    ertodd
    -1.50
    ordable
    -1.41
    weeney
    -1.39
    undreds
    -1.37
    akespeare
    -1.35
    essor
    -1.31
    asio
    -1.30
    akespe
    -1.30
    mone
    -1.27
    ablo
    -1.25
    POSITIVE LOGITS
     Granger
    1.28
     Around
    1.26
     Procedures
    1.25
     Happ
    1.19
     Inquiry
    1.18
     Apart
    1.16
     Grind
    1.15
     Everyday
    1.14
     Magn
    1.12
     Gamb
    1.12
    Activations Density 0.016%

    No Known Activations