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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22826
    Prev
    Next
    INDEX
    Explanations

    words related to digital communication and social media

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

    references to specific individuals or organizations

    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
    2:0.22
    3:0.15
    4:0.04
    5:0.14
    6:0.04
    7:0.02
    8:0.13
    9:0.05
    10:0.07
    11:0.02
    Negative Logits
    ibly
    -1.26
    ographically
    -1.20
    itably
    -1.15
    erous
    -1.09
    ersen
    -1.06
    bery
    -1.06
    ographers
    -1.06
     Whilst
    -1.05
    WARE
    -1.03
     Journals
    -1.03
    POSITIVE LOGITS
    Prim
    1.13
    Rocket
    1.10
    Call
    1.08
    ___
    1.06
    MH
    1.06
    Psy
    1.06
    Legend
    1.05
    brew
    1.05
    dan
    1.04
    Sab
    1.03
    Activations Density 0.016%

    No Known Activations