© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 23391
    Prev
    Next
    INDEX
    Explanations

    conjunctions and various forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    frequency of the word "that" and related verbs expressing future or conditional actions

    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
    3:0.06
    4:0.25
    5:0.05
    6:0.03
    7:0.02
    8:0.21
    9:0.06
    10:0.05
    11:0.02
    Negative Logits
    weed
    -1.48
    bowl
    -1.25
    entimes
    -1.24
    worm
    -1.21
    bler
    -1.16
    esville
    -1.14
    gie
    -1.11
     Blooming
    -1.11
    worker
    -1.10
     essays
    -1.10
    POSITIVE LOGITS
     paternity
    1.51
     unlaw
    1.49
    OPLE
    1.41
    ADRA
    1.32
     agre
    1.31
     allegiance
    1.31
     jurisd
    1.28
    AAF
    1.28
    nance
    1.27
    RT
    1.26
    Activations Density 0.021%

    No Known Activations