INDEX

Explanations

words that indicate the author is experiencing or conveying happiness

oai_token-act-pair · gemini-2.0-flash

glad

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AppComponent

-0.56

routeProvider

-0.55

NgModule

-0.49

wasm

-0.46

fjspx

-0.45

лір

-0.43

apimachinery

-0.43

vue

-0.43

tedrale

-0.43

NSNotification

-0.43

POSITIVE LOGITS

<bos>

1.07

 itſelf

0.70

 kasarigan

0.67

 regretted

0.64

DockStyle

0.63

NewUrlParser

0.61

 GetEnumerator

0.61

 ―――――

0.60

 ſta

0.59

Efq

0.59

Activations Density 1.294%

words that indicate the author is experiencing or conveying happiness

glad

No Comments

No Known Activations