© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 22027
    Prev
    Next
    INDEX
    Explanations

    word endings and linguistic patterns that suggest plurality or continuity

    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
    2:0.14
    3:0.05
    4:0.19
    5:0.06
    6:0.02
    7:0.02
    8:0.17
    9:0.16
    10:0.06
    11:0.03
    Negative Logits
    CLUD
    -1.49
    PART
    -1.47
    INC
    -1.44
    PDATE
    -1.41
    HM
    -1.34
    FORMATION
    -1.32
    PASS
    -1.28
    CI
    -1.28
    CB
    -1.27
    sted
    -1.25
    POSITIVE LOGITS
    ipolar
    1.30
     groove
    1.24
    anga
    1.24
    elo
    1.17
    ipedia
    1.16
     analogy
    1.16
     pouch
    1.14
     bushes
    1.14
    achus
    1.13
    uras
    1.12
    Activations Density 0.007%

    No Known Activations