INDEX

Explanations

phrases expressing gratitude or acknowledgment of a positive contribution

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude or acknowledgment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uve

-0.64

atform

-0.63

mania

-0.58

 desired

-0.57

ength

-0.57

verages

-0.57

riage

-0.56

etus

-0.54

oos

-0.54

]'

-0.52

POSITIVE LOGITS

giving

1.17

to

0.97

 largely

0.86

 partly

0.78

 mainly

0.75

 chiefly

0.74

 primarily

0.70

 thereto

0.68

 mostly

0.67

 solely

0.66

Activations Density 0.023%

phrases expressing gratitude or acknowledgment of a positive contribution

expressions of gratitude or acknowledgment

No Comments

No Known Activations