INDEX

Explanations

key phrases related to diplomacy and international relations

oai_token-act-pair · gpt-3.5-turbo

declarative statements expressing opinions or inquiries

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

Tokens

-0.51

 challeng

-0.50

$$$$

-0.49

 traged

-0.47

ueless

-0.46

artney

-0.46

existent

-0.46

 contrace

-0.46

âĢ¢âĢ¢

-0.45

ONSORED

-0.45

POSITIVE LOGITS

 roundup

0.53

KH

0.52

 Background

0.51

Rac

0.48

Ĥİ

0.48

 summary

0.48

 Sets

0.47

resa

0.47

 Review

0.46

 Transcript

0.46

Activations Density 1.062%

key phrases related to diplomacy and international relations

declarative statements expressing opinions or inquiries

No Comments

No Known Activations