© 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. 3125
    Prev
    Next
    INDEX
    Explanations

    references to chocolate and its potential effects on mood and health

    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
    0:0.04
    1:0.05
    2:0.05
    3:0.07
    4:0.06
    5:0.16
    6:0.04
    7:0.03
    8:0.04
    9:0.12
    10:0.20
    11:0.08
    Negative Logits
    phabet
    -2.14
    gression
    -2.14
     Brow
    -2.12
     Squirrel
    -2.07
    omach
    -2.06
    IOR
    -2.05
    sembly
    -2.03
    phis
    -2.02
    ulla
    -2.02
    stros
    -2.01
    POSITIVE LOGITS
     marketed
    2.44
     interventions
    2.40
     advert
    2.31
     induces
    2.13
     promotes
    2.07
     lect
    2.03
     inaug
    2.01
     selectively
    2.00
     intervention
    2.00
     facilitates
    1.98
    Activations Density 0.013%

    No Known Activations