INDEX

Explanations

questions seeking reasons or explanations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

providedIn

-0.71

NameInMap

-0.65

 AssemblyProduct

-0.65

SerializedSize

-0.65

tagHelperRunner

-0.64

 Савезне

-0.64

SequentialGroup

-0.64

 وتسجيلات

-0.64

MemoryWarning

-0.61

IsMutable

-0.60

POSITIVE LOGITS

why

0.73

Почему

0.70

why

0.64

 اهمیت

0.61

Importance

0.61

ому

0.60

Dlaczego

0.60

 mengapa

0.59

Why

0.59

 importância

0.59

Activations Density 0.222%

questions seeking reasons or explanations

No Comments

No Known Activations