INDEX

Explanations

phrases expressing gratitude

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude or appreciation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gren

-0.68

alse

-0.67

chem

-0.66

arc

-0.66

chemical

-0.66

idth

-0.64

alties

-0.63

ctl

-0.63

UGC

-0.62

paio

-0.61

POSITIVE LOGITS

 contacting

0.96

 patience

0.91

 trusting

0.89

 stopping

0.88

 tuning

0.87

 bothering

0.86

 helping

0.86

 letting

0.86

 visiting

0.86

 noticing

0.85

Activations Density 0.031%

phrases expressing gratitude

expressions of gratitude or appreciation

No Comments

No Known Activations