© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22917
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports team members and their roles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    specific achievements or statistics related to sports players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.04
    2:0.09
    3:0.11
    4:0.04
    5:0.12
    6:0.10
    7:0.05
    8:0.13
    9:0.08
    10:0.11
    11:0.04
    Negative Logits
    sed
    -0.91
     manifest
    -0.90
     ''
    -0.88
     ab
    -0.87
     empt
    -0.87
     Nebraska
    -0.85
     Warfare
    -0.84
     gull
    -0.82
     divers
    -0.81
     aw
    -0.81
    POSITIVE LOGITS
    ================================================================
    1.28
    ogun
    1.24
    mosp
    1.10
    rontal
    1.08
    theless
    1.07
    epad
    1.04
     GOODMAN
    1.00
    -+-+-+-+
    1.00
    roximately
    0.99
     davidjl
    0.99
    Activations Density 0.071%

    No Known Activations