© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 41975
    Prev
    Next
    INDEX
    Explanations

    references to spatial or positional indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.08
    1:0.02
    2:0.04
    3:0.09
    4:0.09
    5:0.03
    6:0.26
    7:0.07
    8:0.06
    9:0.04
    10:0.07
    11:0.10
    Negative Logits
    GGGG
    -1.28
     voyage
    -1.24
    byss
    -1.18
    ELY
    -1.13
    deen
    -1.12
    emouth
    -1.11
     livelihood
    -1.10
     accommodation
    -1.09
     Scrolls
    -1.08
    Way
    -1.08
    POSITIVE LOGITS
    .)
    1.62
    …)
    1.61
    .).
    1.53
    !).
    1.50
     ).
    1.46
    ...)
    1.45
    )!
    1.42
     teasp
    1.42
    ).
    1.40
    olas
    1.40
    Activations Density 0.002%

    No Known Activations