INDEX

Explanations

occurrences of the word "to"

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

according to

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 itſelf

-0.66

 âgé

-0.58

 ſhall

-0.58

 pleaſure

-0.57

 Majefty

-0.57

 enfans

-0.56

 fermés

-0.56

 ProductService

-0.56

 muſt

-0.56

POSITIVE LOGITS

the

0.72

0.60

 Secondo

0.47

 their

0.45

an

0.45

 certain

0.45

 whom

0.44

 consultato

0.43

__(/*!

0.42

Secondo

0.42

Activations Density 0.023%

occurrences of the word "to"

according to

No Comments

No Known Activations