INDEX

Explanations

phrases indicating reasoning and explanations within a text

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

discussion or explanation

np_acts-logits-general · gemini-2.0-flash

discuss and explain

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

 للاسماء

-0.65

PreferredItem

-0.65

 pinulongan

-0.64

 <=",

-0.63

 autorytatywna

-0.63

+#+#

-0.63

 adipis

-0.62

EDEFAULT

-0.61

脚注の使い方

-0.60

AsUp

-0.59

POSITIVE LOGITS

 discussed

1.74

discussed

1.68

 discuss

1.38

explained

1.36

 explained

1.33

 discussion

1.22

 discusses

1.20

 described

1.19

described

1.19

 DISCUSS

1.14

Activations Density 0.680%

phrases indicating reasoning and explanations within a text

discussion or explanation

discuss and explain

No Comments

No Known Activations