INDEX

Explanations

phrases indicating luck or fortune

oai_token-act-pair · gpt-3.5-turbo

words expressing relief or positive outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

gate

-0.71

pled

-0.67

driving

-0.66

 newsletters

-0.65

 kindred

-0.64

QL

-0.64

cair

-0.64

abus

-0.63

zag

-0.61

raised

-0.61

POSITIVE LOGITS

 fortunately

0.92

terday

0.82

nown

0.81

ESA

0.77

udeau

0.72

»Ĵ

0.71

Fortunately

0.70

 luckily

0.69

ï¸

0.67

 thankfully

0.67

Activations Density 0.011%

phrases indicating luck or fortune

words expressing relief or positive outcomes

No Comments

No Known Activations