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. 9-ATT-KK
    6. 117
    Prev
    Next
    INDEX
    Explanations

    situations involving requests for assistance and the response to those requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.06
    3:0.03
    4:0.04
    5:0.03
    6:0.31
    7:0.04
    8:0.11
    9:0.18
    10:0.02
    11:0.03
    Negative Logits
    Barn
    -3.77
     Reyn
    -3.71
     Fish
    -3.61
     pirates
    -3.53
    Terry
    -3.51
     Neil
    -3.47
     fishes
    -3.45
     linen
    -3.42
    urtles
    -3.35
    Neil
    -3.29
    POSITIVE LOGITS
     Kam
    10.37
     CAM
    5.62
     Cham
    5.31
    Wisconsin
    4.55
     Campus
    4.47
     Kum
    4.35
     Parm
    4.34
     Wisconsin
    4.24
     Haas
    4.18
     Champ
    4.11
    Activations Density 0.006%

    No Known Activations