INDEX

Explanations

references to figures, models, and components in scientific or technical documents

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

astéro

-0.50

Statut

-0.46

űr

-0.46

servername

-0.45

})}

-0.45

hæ

-0.45

 still

-0.45

ResponseEntity

-0.44

рс

-0.44

 name

-0.43

POSITIVE LOGITS

Geplaatst

0.77

Билгалдахарш

0.76

 发表于

0.66

ngoing

0.65

esgue

0.62

 disponibilités

0.61

RTDA

0.60

 yore

0.58

είου

0.57

omock

0.56

Activations Density 0.551%

references to figures, models, and components in scientific or technical documents

No Comments

No Known Activations