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. 18841
    Prev
    Next
    INDEX
    Explanations

    references to sports and standings

    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
    0:0.25
    1:0.12
    2:0.02
    3:0.05
    4:0.05
    5:0.15
    6:0.09
    7:0.03
    8:0.04
    9:0.11
    10:0.03
    11:0.01
    Negative Logits
     mourn
    -2.00
     reopened
    -1.97
     revoked
    -1.96
     horrified
    -1.93
     donated
    -1.92
     mourning
    -1.91
     protested
    -1.88
     memorial
    -1.87
     ceremonies
    -1.84
     coroner
    -1.82
    POSITIVE LOGITS
     Basics
    2.90
     Brief
    2.52
     Overview
    2.38
     Introduction
    2.38
     Firstly
    2.37
    %:
    2.30
     Detail
    2.30
     Specifically
    2.29
     vs
    2.26
     Spoiler
    2.25
    Activations Density 0.170%

    No Known Activations