INDEX

Explanations

mentions of the word "yoga"

oai_token-act-pair · gpt-3.5-turbo

terms related to yoga and its culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

etary

-0.88

hyde

-0.88

å£«

-0.82

ilial

-0.75

olver

-0.73

ppelin

-0.73

ly

-0.70

itiveness

-0.69

itions

-0.67

lies

-0.67

POSITIVE LOGITS

 pants

0.82

pants

0.76

Yog

0.72

 Pants

0.70

walk

0.69

 Yoga

0.69

yog

0.68

 flats

0.67

 instructor

0.65

 studios

0.64

Activations Density 0.093%

mentions of the word "yoga"

terms related to yoga and its culture

No Comments

No Known Activations