INDEX

Explanations

medical and scientific terms linked to health effects and toxicity

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

ativement

-0.50

\{\\

-0.49

 metav

-0.46

lock

-0.45

 Decentral

-0.44

?}",

-0.44

aggia

-0.43

toJSON

-0.42

StackNavigator

-0.41

 reversion

-0.41

POSITIVE LOGITS

MigrationBuilder

0.96

Tikang

0.85

DockStyle

0.77

XmlAccessType

0.75

المناصب

0.72

saraba

0.68

MessageState

0.66

 varandra

0.64

bootstrapcdn

0.63

principalColumn

0.63

Activations Density 3.446%

medical and scientific terms linked to health effects and toxicity

No Comments

No Known Activations