INDEX

Explanations

references to growth in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 judiciales

-0.56

setAccessible

-0.56

zeba

-0.55

 Nested

-0.55

 cielo

-0.54

 komis

-0.54

➌

-0.54

deci

-0.53

 canadensis

-0.52

 infierno

-0.52

POSITIVE LOGITS

 growth

3.58

 Growth

3.26

growth

3.24

 GROWTH

3.13

Growth

3.13

GROW

2.51

 growths

2.38

 grow

2.24

 Wachstum

2.19

 GROW

2.17

Activations Density 0.063%

references to growth in various contexts

No Comments

No Known Activations