INDEX

Explanations

the beginning of a document or text segment

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

Follows titles or proper nouns

np_acts-logits-general · gemini-2.0-flash

sets, helpers, we

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

parsedMessage

-0.98

enumi

-0.94

oredCriteria

-0.91

 kaynağından

-0.90

makeConstraints

-0.89

IsContent

-0.85

NameInMap

-0.84

TagMode

-0.81

 كومونز

-0.79

 发表于

-0.77

POSITIVE LOGITS

for

0.57

用于

0.56

 used

0.54

to

0.53

 useful

0.47

します

0.47

 typically

0.47

 consists

0.47

reu

0.46

inga

0.46

Activations Density 0.367%

the beginning of a document or text segment

Follows titles or proper nouns

sets, helpers, we

No Comments

No Known Activations