INDEX

Explanations

expressions of opinion and consensus

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

!("{}",

-0.63

my

-0.62

 myſelf

-0.59

abetes

-0.59

 Baillargeon

-0.55

私の

-0.54

yorum

-0.54

 Majefty

-0.53

ես

-0.53

UserScript

-0.51

POSITIVE LOGITS

 ourselves

1.27

 själva

0.84

our

0.84

Our

0.78

Our

0.73

 знаем

0.70

 nôtre

0.70

OUR

0.68

selves

0.67

+#+#

0.67

Activations Density 0.470%

expressions of opinion and consensus

No Comments

No Known Activations