INDEX

Explanations

instances of the word "assume" and variations, indicating assumptions or presuppositions made in the text

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

 Bracken

-0.71

mela

-0.64

MultipartFile

-0.64

 posteriore

-0.63

 Werken

-0.61

 Region

-0.60

месте

-0.60

 Wilt

-0.60

 igjen

-0.59

 voks

-0.59

POSITIVE LOGITS

 assume

2.46

assume

2.18

 assumes

2.11

 assumed

2.08

 assumption

2.08

 assuming

2.08

 Assume

2.01

 Assumptions

1.98

 assumptions

1.94

Assume

1.90

Activations Density 0.181%

instances of the word "assume" and variations, indicating assumptions or presuppositions made in the text

No Comments

No Known Activations