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

    Neuronpedia

    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. 44080
    Prev
    Next
    INDEX
    Explanations

    references to following in someone's footsteps

    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
    2:0.18
    3:0.05
    4:0.30
    5:0.02
    6:0.07
    7:0.15
    8:0.04
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    hover
    -1.41
    Plex
    -1.39
     Format
    -1.33
    kered
    -1.32
    medium
    -1.32
    question
    -1.30
    DX
    -1.28
    icked
    -1.26
    software
    -1.25
    Media
    -1.23
    POSITIVE LOGITS
     footsteps
    2.17
     herd
    1.58
    abre
    1.56
    verett
    1.48
    roo
    1.44
    utsch
    1.42
    acca
    1.42
    velt
    1.41
     directive
    1.38
    idious
    1.33
    Activations Density 0.003%

    No Known Activations