INDEX

Explanations

terms and concepts related to biological sciences and medical terminology

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

Hentet

-0.78

 שוליים

-0.77

هما

-0.76

TagMode

-0.73

ه

-0.72

ordinaire

-0.66

InSection

-0.64

schule

-0.64

 PopupWindow

-0.63

edal

-0.61

POSITIVE LOGITS

 Chit

0.65

ting

0.63

Wit

0.60

 wits

0.57

SIT

0.55

tingly

0.54

wit

0.54

 inspiração

0.53

licit

0.53

rust

0.52

Activations Density 0.222%

terms and concepts related to biological sciences and medical terminology

No Comments

No Known Activations