© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22718
    Prev
    Next
    INDEX
    Explanations

    details related to sports, including games, teams, and player statistics

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

    specific numerical data or statistics related to rankings or achievements

    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
    1:0.03
    2:0.16
    3:0.05
    4:0.25
    5:0.10
    6:0.03
    7:0.04
    8:0.04
    9:0.07
    10:0.08
    11:0.04
    Negative Logits
    iat
    -1.46
    imming
    -1.43
    wered
    -1.42
    orned
    -1.41
    rador
    -1.40
    ��
    -1.38
    iled
    -1.38
    agar
    -1.37
    alysed
    -1.36
    aran
    -1.36
    POSITIVE LOGITS
     whatsoever
    1.51
     Bulldogs
    1.49
     MSG
    1.44
     Fighters
    1.38
     Blazers
    1.35
     Soccer
    1.34
     Commerce
    1.34
     Franch
    1.31
     Empires
    1.31
    CLASSIFIED
    1.27
    Activations Density 0.014%

    No Known Activations