INDEX

Explanations

pivotal pieces of information related to significant entities and events

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

.

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 disambiguazione

-0.52

 ProtoMessage

-0.50

RegistryLite

-0.48

 ویکی‌پدیا

-0.47

Życiorys

-0.47

jgl

-0.47

IVEREF

-0.46

LayoutPanel

-0.45

CppCodeGen

-0.45

 ujednoznacz

-0.44

POSITIVE LOGITS

 whopping

0.52

 badass

0.44

 AssemblyTitle

0.44

 jamás

0.43

 RIPRODUZIONE

0.40

hütte

0.40

literals

0.40

hynch

0.40

󠁣

0.39

 absolutely

0.38

Activations Density 0.155%

pivotal pieces of information related to significant entities and events

.

No Comments

No Known Activations