INDEX

Explanations

code-related keywords and file handling operations

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

Code snippets with file paths/names

np_acts-logits-general · gemini-2.0-flash

Python code constructs

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

 invokingState

-0.77

 himo

-0.70

 kasarigan

-0.69

脚注の使い方

-0.69

__).

-0.68

✭✭

-0.67

 proposons

-0.66

XmlAccessType

-0.66

hagy

-0.66

Хьажоргаш

-0.66

POSITIVE LOGITS

for

0.44

it

0.43

 posi

0.43

청

0.41

ad

0.40

 account

0.40

 share

0.39

ObjectContext

0.39

ното

0.38

доступ

0.38

Activations Density 0.108%

code-related keywords and file handling operations

Code snippets with file paths/names

Python code constructs

No Comments

No Known Activations