INDEX

Explanations

programming-related annotations or entities in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 kaynağından

-0.69

 تضيفلها

-0.62

 }}$}

-0.56

diğinde

-0.54

leſs

-0.54

xFFFFFF

-0.54

">:

-0.53

 itſelf

-0.53

XmlAccessType

-0.52

geset

-0.52

POSITIVE LOGITS

1.54

at

1.51

1.30

At

1.02

At

1.01

at

0.87

...@

0.82

＠

0.79

AT

0.78

(@

0.75

Activations Density 0.025%

programming-related annotations or entities in code

No Comments

No Known Activations