INDEX

Explanations

occurrences of the word "write" and its variants in different contexts

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

write

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Garza

-0.53

醐

-0.50

UnknownFieldSet

-0.48

طلحات

-0.47

 Saha

-0.46

Chham

-0.45

ชาติ

-0.45

 Trop

-0.44

 uitz

-0.44

 recomendo

-0.44

POSITIVE LOGITS

 write

1.64

 writing

1.59

 Writing

1.48

write

1.48

Writing

1.46

 Write

1.45

Write

1.43

 written

1.41

 wrote

1.38

 writes

1.37

Activations Density 0.081%

occurrences of the word "write" and its variants in different contexts

write

No Comments

No Known Activations