INDEX

Explanations

instances of the verb "write" and its variations related to writing activities

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

awtextra

-0.85

ConstraintMaker

-0.73

unhofer

-0.69

etheless

-0.68

BagConstraints

-0.68

พาะ

-0.67

 localObject

-0.67

Ỉ

-0.66

requireNonNull

-0.66

 /\.(

-0.66

POSITIVE LOGITS

 write

2.48

 wrote

2.26

write

2.21

 writes

2.09

Write

2.05

 writing

2.05

 Write

2.02

 WRITE

1.94

wrote

1.80

 Writing

1.80

Activations Density 0.073%

instances of the verb "write" and its variations related to writing activities

No Comments

No Known Activations