INDEX

Explanations

frequent imports in code-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 GlobalKey

-0.91

 ddelweddau

-0.78

RTEE

-0.77

存于互联网档案馆

-0.73

 onAnimation

-0.72

typeorm

-0.71

########.

-0.68

NOPQRST

-0.67

EDEFAULT

-0.67

Initializable

-0.67

POSITIVE LOGITS

import

0.90

 culte

0.57

 import

0.56

︎

0.55

 identifiés

0.54

️

0.49

 Vergara

0.49

 IMPORT

0.49

なりません

0.48

 labios

0.48

Activations Density 0.018%

frequent imports in code-related contexts

No Comments

No Known Activations