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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22746
    Prev
    Next
    INDEX
    Explanations

    past tense verbs ending in 'ed'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to occurrences or events that have happened recently

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    1:0.02
    2:0.16
    3:0.07
    4:0.27
    5:0.06
    6:0.03
    7:0.02
    8:0.11
    9:0.09
    10:0.04
    11:0.02
    Negative Logits
     Logged
    -1.58
    irez
    -1.39
    ammad
    -1.25
    naissance
    -1.25
    argon
    -1.25
    vez
    -1.24
    ategories
    -1.24
     Unloaded
    -1.23
    vector
    -1.20
    uga
    -1.17
    POSITIVE LOGITS
     reconc
    1.37
     Count
    1.32
     neighbours
    1.25
     accuser
    1.25
     adjourn
    1.22
     Happ
    1.22
     neighbour
    1.20
     jo
    1.18
     inverse
    1.18
    Norm
    1.17
    Activations Density 0.001%

    No Known Activations