© 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. 2-ATT-KK
    11. 22514
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes or stories written in first person perspective

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

    phrases expressing personal feelings and opinions

    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
    0:0.08
    1:0.04
    2:0.11
    3:0.07
    4:0.03
    5:0.10
    6:0.06
    7:0.06
    8:0.10
    9:0.13
    10:0.12
    11:0.05
    Negative Logits
     predec
    -1.33
     differe
    -1.29
     reperc
    -1.19
     detrim
    -1.15
     paran
    -1.14
     disadvant
    -1.14
     foothold
    -1.13
    ulton
    -1.09
     aggregation
    -1.06
     dexter
    -1.06
    POSITIVE LOGITS
     myself
    1.28
    igans
    1.21
    lished
    1.14
    obic
    1.11
    eur
    1.11
    aniel
    1.10
    ل
    1.09
    ////////////////////////////////
    1.08
     tears
    1.07
     :=
    1.07
    Activations Density 0.041%

    No Known Activations