INDEX

Explanations

references to the English language and its usage

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

"English" or other languages

np_acts-logits-general · gemini-2.0-flash

English language and versions

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

ConstraintMaker

-0.97

 createState

-0.96

sizeCache

-0.94

SourceChecksum

-0.90

Tikang

-0.88

NameInMap

-0.87

mybatisplus

-0.87

tagHelperRunner

-0.87

Hochspringen

-0.86

$_"

-0.85

POSITIVE LOGITS

 language

0.58

 words

0.55

 speaking

0.55

sprach

0.53

 version

0.52

 spoken

0.52

speaking

0.50

 Version

0.49

language

0.47

圏

0.46

Activations Density 0.272%

references to the English language and its usage

"English" or other languages

English language and versions

No Comments

No Known Activations