INDEX

Explanations

terms related to medical research and pathophysiology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

]),

-0.52

 JpaRepository

-0.48

brainly

-0.47

 ویکی‌پدیا

-0.47

'\\

-0.46

Predecesor

-0.46

Portály

-0.46

Архівовано

-0.45

ualitas

-0.43

‘

-0.41

POSITIVE LOGITS

 myſelf

0.85

 Chriſt

0.81

 ſche

0.79

 Theſe

0.78

 leaſt

0.76

 faſt

0.75

 houſe

0.74

 Chriftian

0.73

 Houſe

0.72

 saites

0.72

Activations Density 0.504%

terms related to medical research and pathophysiology

No Comments

No Known Activations