INDEX

Explanations

phrases that denote conclusions or final statements

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

 ویکی‌پدیا

-0.88

ViewImports

-0.83

 Baillargeon

-0.83

########.

-0.73

 réguli

-0.68

dolu

-0.67

новништво

-0.63

OGND

-0.63

 للمعارف

-0.62

 JpaRepository

-0.61

POSITIVE LOGITS

 ultimately

1.17

Ultimately

1.12

 Ultimately

1.12

 uiteindelijk

0.90

 letzt

0.89

 finalement

0.87

indelijk

0.77

 finally

0.77

 eventually

0.76

結局

0.75

Activations Density 0.101%

phrases that denote conclusions or final statements

No Comments

No Known Activations