INDEX

Explanations

key terms related to health issues and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

+#+#

-0.75

Jîn

-0.66

 الحره

-0.63

 становника

-0.62

 للاسماء

-0.61

adpleegd

-0.57

 мәкал

-0.57

 snippetHide

-0.54

statechange

-0.53

ilead

-0.53

POSITIVE LOGITS

 caused

2.51

caused

2.13

due

2.08

 Caused

1.99

due

1.87

 causado

1.80

 akibat

1.70

 resulting

1.68

 occasioned

1.64

DUE

1.62

Activations Density 1.497%

key terms related to health issues and medical conditions

No Comments

No Known Activations