INDEX

Explanations

terms related to electronics and electrical components

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 naturelle

-0.64

IsContent

-0.55

 թվական

-0.53

 الحره

-0.53

最快更新

-0.50

 constaté

-0.49

Tug

-0.49

acres

-0.49

 GenerationType

-0.47

warzys

-0.47

POSITIVE LOGITS

 Electronics

0.79

 Toshiba

0.76

 electronics

0.72

 appliances

0.72

 Appliance

0.72

Electronics

0.70

 appliance

0.68

 Appliances

0.67

তথ্যসূত্র

0.66

TVs

0.62

Activations Density 0.333%

terms related to electronics and electrical components

No Comments

No Known Activations