Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 8608
    Prev
    Next
    INDEX
    Explanations

    phrases related to employment and professional positions

    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
    2:0.05
    3:0.03
    4:0.01
    5:0.06
    6:0.09
    7:0.44
    8:0.05
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
     surrog
    -1.39
     recapt
    -1.36
     stabilization
    -1.29
     correlations
    -1.26
     dissatisf
    -1.26
     boil
    -1.23
     cohesion
    -1.20
    Interstitial
    -1.20
    rontal
    -1.18
     qualitative
    -1.17
    POSITIVE LOGITS
    whose
    1.38
     whom
    1.33
    ��
    1.27
    iHUD
    1.23
     whose
    1.22
    who
    1.20
    hid
    1.16
    afort
    1.14
     tem
    1.13
    Joined
    1.12
    Activations Density 0.824%

    No Known Activations