INDEX

Explanations

references to the functionality and effectiveness of tools or resources

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

Followed by "so"

np_acts-logits-general · gemini-2.0-flash

so much, so little, such

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 بيها

-0.67

=$?

-0.63

 jadx

-0.60

 HasFactory

-0.59

Kelebihan

-0.57

énéral

-0.53

noons

-0.52

Alguna

-0.52

ReusableCell

-0.51

wnież

-0.51

POSITIVE LOGITS

 such

2.58

such

2.18

Such

2.07

 Such

2.00

 SUCH

1.87

so

1.87

如此

1.86

 столь

1.85

 tão

1.84

這麼

1.80

Activations Density 0.698%

references to the functionality and effectiveness of tools or resources

Followed by "so"

so much, so little, such

No Comments

No Known Activations