INDEX

Explanations

terms and concepts related to ethics and medical research frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cros

-0.57

'}>

-0.54

adina

-0.51

volmente

-0.50

이션

-0.49

/">

-0.49

)">

-0.48

CONTENT

-0.47

꿔

-0.46

ENTIALS

-0.45

POSITIVE LOGITS

IST

1.21

ISH

1.11

ish

1.04

ISM

1.04

ist

1.01

isman

1.00

isk

0.97

iste

0.97

IS

0.95

isme

0.91

Activations Density 2.829%

terms and concepts related to ethics and medical research frameworks

No Comments

No Known Activations