© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 42960
    Prev
    Next
    INDEX
    Explanations

    phrases highlighting collective experiences or shared identities

    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
    0:0.05
    1:0.02
    2:0.11
    3:0.07
    4:0.07
    5:0.04
    6:0.17
    7:0.11
    8:0.07
    9:0.04
    10:0.10
    11:0.12
    Negative Logits
     departure
    -1.41
    Quotes
    -1.31
     Heist
    -1.29
     Decay
    -1.28
     Changes
    -1.19
    Diff
    -1.18
    Plugin
    -1.18
     Bulgar
    -1.17
     Overs
    -1.16
     Appearance
    -1.16
    POSITIVE LOGITS
    pires
    1.66
    ozo
    1.65
    audi
    1.55
    regor
    1.44
    iatrics
    1.41
    bett
    1.32
     cautioned
    1.32
     pond
    1.27
    urbed
    1.27
    ynes
    1.26
    Activations Density 0.003%

    No Known Activations