INDEX

Explanations

technical terms and acronyms related to scientific and computing contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Tembelea

-0.97

extAlignment

-0.94

 referenties

-0.90

 getItemId

-0.90

fillType

-0.87

oughly

-0.86

HasAnnotation

-0.83

findpost

-0.83

 الدولى

-0.82

NLA

-0.82

POSITIVE LOGITS

cic

1.08

ac

1.03

lec

1.01

Koc

1.00

ics

0.99

Buc

0.98

Kac

0.97

Buc

0.97

ic

0.95

ic

0.94

Activations Density 2.809%

technical terms and acronyms related to scientific and computing contexts

No Comments

No Known Activations