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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 18388
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their performance or strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.13
    3:0.19
    4:0.06
    5:0.07
    6:0.03
    7:0.02
    8:0.05
    9:0.16
    10:0.12
    11:0.06
    Negative Logits
    ],"
    -1.73
    "],"
    -1.53
    ]}
    -1.46
    ]."
    -1.46
    "))
    -1.45
    yip
    -1.43
    ゴン
    -1.42
    cellaneous
    -1.41
    "?
    -1.41
    ])
    -1.36
    POSITIVE LOGITS
     however
    1.94
     meanwhile
    1.68
     understandably
    1.64
     certainly
    1.63
     famously
    1.45
     obviously
    1.44
    ogun
    1.40
     rightly
    1.40
     therefore
    1.38
     doubtless
    1.32
    Activations Density 0.494%

    No Known Activations