INDEX

Explanations

terms related to data manipulation and transformation processes

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

Transformation or division "into" something

np_acts-logits-general · gemini-2.0-flash

divided into

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

لمانيا

-0.43

Auf

-0.41

 lopp

-0.40

OPH

-0.40

oph

-0.39

ICom

-0.38

Binder

-0.37

TypeDef

-0.37

 AssemblyTitle

-0.36

柄

-0.36

POSITIVE LOGITS

 into

2.56

 Into

1.93

into

1.90

Into

1.84

 INTO

1.78

INTO

1.54

 thành

1.25

 menjadi

1.14

 Menjadi

1.03

成

0.93

Activations Density 0.362%

terms related to data manipulation and transformation processes

Transformation or division "into" something

divided into

No Comments

No Known Activations