INDEX

Explanations

elements related to questions and responses, particularly in the context of categorization and correctness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 faveur

-0.52

 étoient

-0.51

yntaxException

-0.50

 familières

-0.50

styleType

-0.50

咙

-0.50

 AssemblyTitle

-0.49

XmlAccessType

-0.49

 dévelo

-0.49

 église

-0.48

POSITIVE LOGITS

nb

0.66

Aj

0.60

MAJ

0.60

nb

0.59

bdd

0.59

nom

0.58

BDD

0.57

 recuper

0.56

Nom

0.56

Aj

0.56

Activations Density 0.175%

elements related to questions and responses, particularly in the context of categorization and correctness

No Comments

No Known Activations