INDEX

Explanations

recent time-related events or occurrences

oai_token-act-pair · gpt-3.5-turbo

the word "Recently" and its variations, indicating recent events or updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 ending

-0.75

 stead

-0.70

 sign

-0.69

 stamped

-0.69

 signs

-0.67

 finish

-0.67

 breathing

-0.66

 pony

-0.66

 continuity

-0.65

 equivalent

-0.64

POSITIVE LOGITS

Recently

3.30

 Recently

2.95

recent

2.00

Recent

1.86

Yesterday

1.68

 recently

1.65

 Recent

1.62

Currently

1.57

 lately

1.48

Earlier

1.38

Activations Density 0.013%

recent time-related events or occurrences

the word "Recently" and its variations, indicating recent events or updates

No Comments

No Known Activations