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. 1-ATT-KK
    6. 6355
    Prev
    Next
    INDEX
    Explanations

    information related to American football players and their positions and performance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    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
    1:0.07
    2:0.13
    3:0.06
    4:0.09
    5:0.05
    6:0.05
    7:0.14
    8:0.07
    9:0.04
    10:0.12
    11:0.09
    Negative Logits
     ®
    -0.99
     Authors
    -0.89
     authors
    -0.86
    microsoft
    -0.83
    pend
    -0.81
    Panel
    -0.81
    irs
    -0.80
     IBM
    -0.79
     000
    -0.77
    cul
    -0.77
    POSITIVE LOGITS
     teammate
    1.41
     rookie
    1.41
     Rookie
    1.35
     Athletic
    1.29
     teammates
    1.20
     coached
    1.18
     offensively
    1.18
     defensively
    1.18
     preseason
    1.17
     rookies
    1.15
    Activations Density 0.780%

    No Known Activations