INDEX

Explanations

phrases and terms related to medical and health-related conditions

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

 فريبيس

-0.87

WithMany

-0.73

IsMutable

-0.70

 GenerationType

-0.68

RenderAtEndOf

-0.68

migrationBuilder

-0.66

IsContent

-0.64

GeneratedValue

-0.62

buttonBar

-0.58

 vectorielles

-0.57

POSITIVE LOGITS

DEFINE

0.52

quería

0.51

hyperref

0.50

 Whistle

0.48

queria

0.47

 kolei

0.47

 Amiens

0.47

くれます

0.47

 supers

0.47

 собой

0.47

Activations Density 0.831%

phrases and terms related to medical and health-related conditions

No Comments

No Known Activations