INDEX

Explanations

blocks of code and data structures, particularly involving object and function definitions

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

Code snippets or code-related text

np_acts-logits-general · gemini-2.0-flash

code or technical text

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

Portály

-0.67

出版年

-0.65

NSNotification

-0.64

 незавершена

-0.63

 للمعارف

-0.61

 UserDao

-0.58

amaño

-0.57

Spoljašnje

-0.57

BagConstraints

-0.57

ghijklmnop

-0.57

POSITIVE LOGITS

↵

2.11

↵↵

1.57

↵↵↵

1.14

↵↵↵↵

0.91

0.84

↵↵↵↵↵

0.82

0.76

//

0.71

</h3>

0.69

↵↵↵↵↵↵↵

0.66

Activations Density 0.293%

blocks of code and data structures, particularly involving object and function definitions

Code snippets or code-related text

code or technical text

No Comments

No Known Activations