INDEX

Explanations

instances of the word "born" related to personal or biographical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

lə

-0.67

Xie

-0.66

 McCabe

-0.65

Xie

-0.65

currentItem

-0.64

adlo

-0.61

tti

-0.61

the

-0.61

################

-0.59

migrationBuilder

-0.58

POSITIVE LOGITS

 BORN

2.17

 born

2.15

 Born

1.96

Born

1.89

born

1.83

BORN

1.81

 geboren

1.38

 birth

1.36

 Birth

1.27

 Borne

1.27

Activations Density 0.073%

instances of the word "born" related to personal or biographical information

No Comments

No Known Activations