INDEX

Explanations

abbreviations and acronyms related to scientific and medical terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.68

cel

-0.60

kom

-0.54

↵↵

-0.53

 aber

-0.52

pas

-0.52

kor

-0.51

Mak

-0.51

-0.50

CEPT

-0.50

POSITIVE LOGITS

 raiſ

1.05

__":

1.01

 myſelf

0.99

 ſtate

0.99

TypedDataSet

0.95

 Majefty

0.93

 ſch

0.93

__':

0.92

 ſta

0.92

 houſe

0.92

Activations Density 0.369%

abbreviations and acronyms related to scientific and medical terms

No Comments

No Known Activations