INDEX

Explanations

phrases that express positive feedback or appreciation

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

Sentences broken by ellipses

np_acts-logits-general · gemini-2.0-flash

Continue reading, etc

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

windowFixed

-1.11

 мәкал

-0.97

stdc

-0.78

 चीज़ों

-0.77

 useAuth

-0.77

Efq

-0.76

новништво

-0.75

WebVitals

-0.75

таратура

-0.74

protoc

-0.73

POSITIVE LOGITS

or

0.86

<eos>

0.82

etc

0.76

↵↵

0.74

and

0.73

for

0.71

...

0.70

الخ

0.69

/...

0.68

↵↵↵

0.67

Activations Density 0.099%

phrases that express positive feedback or appreciation

Sentences broken by ellipses

Continue reading, etc

No Comments

No Known Activations