INDEX

Explanations

the word "would"

oai_token-act-pair · gpt-3.5-turbo

phrases expressing hypothetical scenarios or desires

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Cook

-0.67

rylic

-0.66

Pie

-0.65

isted

-0.65

æ³

-0.65

values

-0.64

resources

-0.63

Kag

-0.63

Reporting

-0.62

story

-0.61

POSITIVE LOGITS

 surely

1.02

 doubtless

0.98

be

0.98

 undoubtedly

0.97

 inevitably

0.94

 never

0.92

 gladly

0.90

 probably

0.89

 invariably

0.89

 suffice

0.87

Activations Density 0.160%

the word "would"

phrases expressing hypothetical scenarios or desires

No Known Activations