© 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. 22915
    Prev
    Next
    INDEX
    Explanations

    references to physical strength and size

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

    modifications or enhancements to existing systems or processes

    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
    2:0.20
    3:0.07
    4:0.25
    5:0.04
    6:0.02
    7:0.03
    8:0.08
    9:0.12
    10:0.04
    11:0.03
    Negative Logits
    pta
    -1.42
    uyomi
    -1.33
     Pradesh
    -1.31
    ichita
    -1.30
    OSP
    -1.30
    anco
    -1.29
    iris
    -1.27
    eper
    -1.26
    JECT
    -1.26
    nces
    -1.25
    POSITIVE LOGITS
     carriage
    1.42
     tires
    1.36
     tyres
    1.35
     endeavour
    1.24
     camel
    1.22
     pork
    1.22
     stout
    1.22
     rescue
    1.20
     tart
    1.19
     tyre
    1.19
    Activations Density 0.005%

    No Known Activations