INDEX

Explanations

phrases related to interactions and actions taken by different entities

oai_token-act-pair · gpt-3.5-turbo

negations or instances of unfair treatment in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Nare

-0.63

ocument

-0.58

nesday

-0.58

renheit

-0.56

FTWARE

-0.56

Queue

-0.54

ayson

-0.53

egu

-0.53

aea

-0.53

erenn

-0.52

POSITIVE LOGITS

\":

0.50

 awaits

0.49

 thereof

0.48

':

0.48

 contagious

0.48

zbollah

0.47

 awaited

0.47

 everlasting

0.46

 âĢº

0.46

 ensuing

0.45

Activations Density 0.387%

phrases related to interactions and actions taken by different entities

negations or instances of unfair treatment in various contexts

No Comments

No Known Activations