INDEX

Explanations

phrases indicating confusion or uncertainty, particularly regarding belief or direction

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

was

-0.68

Was

-0.66

was

-0.66

Was

-0.66

 wasn

-0.64

 وكان

-0.60

وكان

-0.59

كانت

-0.59

 buvo

-0.59

had

-0.59

POSITIVE LOGITS

########.

0.87

 оригіналу

0.82

клопе

0.80

 للاسماء

0.78

 kaynağından

0.69

 autorytatywna

0.69

 الحره

0.66

पया

0.66

 समीक्षाएं

0.65

endphp

0.64

Activations Density 0.417%

phrases indicating confusion or uncertainty, particularly regarding belief or direction

No Comments

No Known Activations