INDEX

Explanations

instances of the word "define" and its variations, indicating a focus on defining concepts or terms

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

passenger

-0.46

Passenger

-0.46

 passenger

-0.43

Passengers

-0.43

Money

-0.43

 ater

-0.42

 passagers

-0.42

 Passenger

-0.42

passengers

-0.41

Noter

-0.40

POSITIVE LOGITS

 Define

1.13

 Defines

1.06

 defines

1.01

 define

1.00

Define

0.99

Defining

0.96

 Defining

0.94

 Defin

0.94

 defin

0.92

 defining

0.92

Activations Density 0.060%

instances of the word "define" and its variations, indicating a focus on defining concepts or terms

No Comments

No Known Activations