INDEX

Explanations

texts with a focus on multi-lingual contents, particularly certain scripts or characters from various languages

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

Rare, non-English characters and symbols

np_acts-logits-general · gemini-2.0-flash

currency symbols, code, and non-Latin characters

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.67

Kjelder

-0.60

անո

-0.49

fla

-0.49

 really

-0.48

 Lombardo

-0.46

ABORT

-0.46

addCriterion

-0.46

FirstResponder

-0.45

OPHY

-0.45

POSITIVE LOGITS

RenderAtEndOf

0.83

#+#

0.81

+#+

0.80

+:+

0.77

UrlResolution

0.75

IMPORTED

0.73

 незавершена

0.72

ezers

0.70

/<

0.68

 ExecuteAsync

0.68

Activations Density 0.003%

texts with a focus on multi-lingual contents, particularly certain scripts or characters from various languages

Rare, non-English characters and symbols

currency symbols, code, and non-Latin characters

No Comments

No Known Activations