INDEX

Explanations

words indicating an impending occurrence or future actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 BoxDecoration

-0.70

welche

-0.63

いても

-0.63

providedIn

-0.60

fabrik

-0.58

itage

-0.58

としての

-0.58

-0.57

yam

-0.57

illips

-0.57

POSITIVE LOGITS

 soon

3.46

 Soon

3.12

soon

3.11

Soon

3.10

 SOON

2.83

 bientôt

1.99

 foon

1.98

 sooner

1.95

 snart

1.94

 shortly

1.82

Activations Density 0.061%

words indicating an impending occurrence or future actions

No Comments

No Known Activations