INDEX

Explanations

references to user reviews and ratings

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

 égale

-0.54

 considérons

-0.51

 remplace

-0.49

 assistenza

-0.49

 bambou

-0.49

 vPvB

-0.48

 lettore

-0.47

 aéreo

-0.46

자인

-0.45

 Schriften

-0.45

POSITIVE LOGITS

 pinulongan

0.75

NameInMap

0.68

########.

0.65

ReusableCell

0.63

PerformLayout

0.63

Clik

0.61

Portail

0.58

enumi

0.58

 يتيمه

0.57

 <<<<<<<<<<<<<<

0.57

Activations Density 0.335%

references to user reviews and ratings

No Comments

No Known Activations