INDEX

Explanations

phrases expressing gratitude or acknowledgment of someone/something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "thanks" indicating 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atform

-0.74

ago

-0.69

oto

-0.64

adel

-0.64

å¥³

-0.63

avis

-0.62

estern

-0.62

otal

-0.62

ength

-0.62

 Rebell

-0.61

POSITIVE LOGITS

giving

1.46

fully

0.74

ESCO

0.71

dropping

0.71

ĸļ

0.71

cription

0.70

 diligence

0.69

CU

0.67

ifully

0.66

gers

0.65

Activations Density 0.017%

phrases expressing gratitude or acknowledgment of someone/something

instances of the word "thanks" indicating gratitude or acknowledgment

No Comments

No Known Activations