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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8927
    Prev
    Next
    INDEX
    Explanations

    references to companies and financial metrics

    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
    0:0.05
    1:0.06
    2:0.01
    3:0.07
    4:0.03
    5:0.09
    6:0.10
    7:0.24
    8:0.08
    9:0.07
    10:0.02
    11:0.12
    Negative Logits
    �
    -2.40
    CHAPTER
    -2.36
    Interstitial
    -2.22
    pleasant
    -2.18
    ursion
    -2.10
    vable
    -2.10
    endum
    -2.04
    ursions
    -2.04
    ocious
    -2.02
    uties
    -2.01
    POSITIVE LOGITS
     IBM
    3.32
     Hew
    3.27
     Motorola
    3.13
     JPMorgan
    3.12
     Samsung
    3.11
     Microsoft
    3.07
     Nokia
    3.04
     Siem
    2.90
     Pepsi
    2.89
     Panasonic
    2.86
    Activations Density 0.101%

    No Known Activations