© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 3253
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to performance metrics

    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
    0:0.10
    1:0.05
    2:0.13
    3:0.09
    4:0.06
    5:0.06
    6:0.04
    7:0.03
    8:0.07
    9:0.11
    10:0.10
    11:0.10
    Negative Logits
    yip
    -1.44
    kef
    -1.43
    nown
    -1.38
    psey
    -1.32
    wig
    -1.31
    abal
    -1.31
     scrut
    -1.28
    undai
    -1.27
    ndum
    -1.24
    staking
    -1.23
    POSITIVE LOGITS
    RELATED
    1.18
    Buff
    1.16
    },
    1.14
     receivers
    1.13
     Balanced
    1.10
     Gain
    1.09
    OURCE
    1.08
    Years
    1.07
     fibers
    1.06
     Composite
    1.06
    Activations Density 0.010%

    No Known Activations