INDEX

Explanations

phrases indicating future hypothetical scenarios

oai_token-act-pair · gpt-3.5-turbo

the word "would" indicating hypothetical situations or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

rylic

-0.69

æ³

-0.68

isted

-0.64

Reporting

-0.62

 Basics

-0.60

oran

-0.60

Writing

-0.60

 Jelly

-0.60

ished

-0.59

 Case

-0.59

POSITIVE LOGITS

 surely

1.01

 doubtless

0.94

 never

0.91

be

0.91

 undoubtedly

0.90

 sugg

0.89

 inevitably

0.89

ĸļ

0.87

 imply

0.86

 definitely

0.82

Activations Density 0.117%

phrases indicating future hypothetical scenarios

the word "would" indicating hypothetical situations or consequences

No Comments

No Known Activations