INDEX

Explanations

specific terms and phrases related to recommendations or advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

áp

-0.53

>>()

-0.53

")));

-0.51

ra

-0.49

 ۱۳۹

-0.49

 gerekti

-0.48

"))

-0.48

ddots

-0.48

ínio

-0.48

POSITIVE LOGITS

AxisAlignment

0.98

 للمعارف

0.96

VersionUID

0.96

NameInMap

0.81

μός

0.76

ècie

0.76

ViewImports

0.74

 ejus

0.73

 Профиль

0.71

 ujednoznacz

0.71

Activations Density 0.108%

specific terms and phrases related to recommendations or advice

No Comments

No Known Activations