INDEX

Explanations

phrases that indicate important medical warnings and advice related to medication and health conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Buffer

-0.45

ison

-0.43

فر

-0.42

pub

-0.42

牌

-0.40

Res

-0.40

apollo

-0.40

awa

-0.39

werkt

-0.39

res

-0.39

POSITIVE LOGITS

 suspicious

0.96

 suspiciously

0.92

Unusual

0.84

 Unusual

0.82

 Paglinawan

0.81

 unexplained

0.81

脚注の使い方

0.81

 strangest

0.80

unusual

0.79

 itſelf

0.78

Activations Density 0.336%

phrases that indicate important medical warnings and advice related to medication and health conditions

No Comments

No Known Activations