INDEX

Explanations

the repeated occurrences of the word "times."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 pocos

-0.65

PostExecute

-0.60

 pochi

-0.55

äische

-0.53

few

-0.53

metis

-0.53

upol

-0.53

jene

-0.53

 Theſe

-0.52

edn

-0.52

POSITIVE LOGITS

twice

1.27

 twice

1.24

Twice

1.21

 thrice

1.13

 Twice

1.03

 TWICE

1.01

 ganger

0.94

 vezes

0.93

 veces

0.86

三次

0.85

Activations Density 0.109%

the repeated occurrences of the word "times."

No Comments

No Known Activations