INDEX

Explanations

headings and sections related to information about authors, books, and articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

########.

-0.77

 tantum

-0.68

الدراسه

-0.64

GenerationType

-0.61

adpleegd

-0.61

TagHelper

-0.58

LayoutStyle

-0.57

GraphicsUnit

-0.57

 distanciation

-0.56

UseVisualStyle

-0.56

POSITIVE LOGITS

]-->

0.61

 ujednoznacz

0.61

曖昧さ回避

0.58

stateProvider

0.55

的其他

0.55

+#+#

0.54

ArgsConstructor

0.53

épend

0.52

FIN

0.52

typeorm

0.52

Activations Density 0.199%

headings and sections related to information about authors, books, and articles

No Comments

No Known Activations