© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 46868
    Prev
    Next
    INDEX
    Explanations

    references to direction or positional descriptions, particularly in discussions about progress or change

    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
    0:0.02
    1:0.01
    2:0.08
    3:0.05
    4:0.16
    5:0.04
    6:0.11
    7:0.24
    8:0.06
    9:0.04
    10:0.07
    11:0.08
    Negative Logits
     moot
    -1.26
     reapp
    -1.25
    acle
    -1.21
     entrance
    -1.18
    atisf
    -1.15
     manifest
    -1.13
    PLIED
    -1.13
     fate
    -1.11
     omission
    -1.11
     potency
    -1.10
    POSITIVE LOGITS
    ertodd
    1.61
    ipeg
    1.51
    thia
    1.44
     toget
    1.43
    rador
    1.41
    family
    1.38
    ourage
    1.38
    anchester
    1.37
    �
    1.36
    ################
    1.34
    Activations Density 0.001%

    No Known Activations