INDEX

Explanations

references to possessive pronouns such as "its" and "their"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

TagMode

-0.46

 questão

-0.44

 defaultstate

-0.44

ArgumentParser

-0.43

addPreferredGap

-0.43

 yrity

-0.41

 things

-0.40

 quería

-0.40

assertThat

-0.40

beginTransaction

-0.40

POSITIVE LOGITS

 contents

1.09

 predecessor

0.99

 entirety

0.98

 origins

0.97

 namesake

0.95

hould

0.94

 existence

0.93

 occupants

0.92

 inhabitants

0.90

 inception

0.89

Activations Density 0.373%

references to possessive pronouns such as "its" and "their"

No Comments

No Known Activations