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. 7-ATT-KK
    6. 9429
    Prev
    Next
    INDEX
    Explanations

    elements discussing beliefs and definitions related to ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    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
    1:0.05
    2:0.02
    3:0.16
    4:0.06
    5:0.22
    6:0.04
    7:0.02
    8:0.08
    9:0.19
    10:0.01
    11:0.02
    Negative Logits
    oday
    -2.74
    PDATE
    -2.69
    anwhile
    -2.67
    terday
    -2.57
    cember
    -2.33
    tip
    -2.30
    wagen
    -2.30
     confir
    -2.22
    版
    -2.22
    nesday
    -2.21
    POSITIVE LOGITS
     conflicts
    2.33
     relationships
    2.26
     conflict
    2.22
     presupp
    2.17
     relational
    2.15
     unstable
    2.14
     finite
    2.12
     entails
    2.10
    types
    2.08
     inherently
    2.06
    Activations Density 0.001%

    No Known Activations