INDEX

Explanations

instances of the word "new"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

########.

-0.97

 Linus

-0.78

RenderAtEndOf

-0.73

 endwhile

-0.62

 isoto

-0.61

 UserDao

-0.61

 Neighbors

-0.61

NOK

-0.61

 Effort

-0.60

iis

-0.60

POSITIVE LOGITS

new

0.87

new

0.67

 nouveaux

0.60

 новая

0.57

 nuevos

0.57

 nuove

0.55

 nuovi

0.55

 nuevo

0.55

 nuevas

0.54

Activations Density 0.125%

instances of the word "new"

No Comments

No Known Activations