INDEX

Explanations

words and phrases that consistently appear multiple times in relation to quantities or time duration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

findElement

-0.77

Wpf

-0.73

énario

-0.73

djangoproject

-0.72

Fixtures

-0.70

ープ

-0.69

 Tint

-0.68

🐥

-0.66

jms

-0.65

inquirer

-0.65

POSITIVE LOGITS

 OVER

1.57

 over

1.53

 Over

1.52

over

1.46

Over

1.43

OVER

1.31

 Overs

1.31

 Overton

1.20

overs

1.19

Overs

1.15

Activations Density 0.118%

words and phrases that consistently appear multiple times in relation to quantities or time duration

No Comments

No Known Activations