INDEX

Explanations

elements relating to recommendations and evaluations of products or experiences

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

"this"

np_acts-logits-general · gemini-2.0-flash

this

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 وہ

-0.53

/**/*.

-0.44

かれて

-0.43

่านั้น

-0.43

ੱਕ

-0.42

toor

-0.42

 Then

-0.41

Then

-0.41

/>,

-0.40

englanniksi

-0.40

POSITIVE LOGITS

 this

3.40

this

2.79

 these

2.09

 này

2.02

 questa

1.99

This

1.97

 dieses

1.96

 этой

1.94

 THIS

1.93

 acestui

1.92

Activations Density 2.455%

elements relating to recommendations and evaluations of products or experiences

"this"

this

No Comments

No Known Activations