INDEX

Explanations

attributes and descriptors related to quality and suitability in various contexts

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

Prepositions followed by nouns

np_acts-logits-general · gemini-2.0-flash

for/to/which

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

igshid

-0.79

 تضيفلها

-0.77

nocache

-0.73

+:+

-0.66

MemoryWarning

-0.65

'<?

-0.65

исленность

-0.65

脚注の使い方

-0.65

gorithm

-0.63

 Jefus

-0.63

POSITIVE LOGITS

to

1.12

for

0.72

 which

0.65

 để

0.62

 Which

0.62

 waarop

0.59

 wherewith

0.58

Which

0.57

 auquel

0.57

 auxquelles

0.57

Activations Density 0.257%

attributes and descriptors related to quality and suitability in various contexts

Prepositions followed by nouns

for/to/which

No Comments

No Known Activations