INDEX

Explanations

phrases indicating exceptions or exclusions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating exceptions or exclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 largeDownload

-0.67

soType

-0.65

Constructed

-0.62

igure

-0.62

 WATCHED

-0.61

ustration

-0.61

ONSORED

-0.60

rift

-0.60

figure

-0.58

 embold

-0.57

POSITIVE LOGITS

 ones

1.31

 ours

1.17

 yours

1.15

 those

1.12

those

1.03

 hers

1.03

 theirs

0.94

 Ones

0.82

 mine

0.70

one

0.69

Activations Density 0.260%

phrases indicating exceptions or exclusions

phrases indicating exceptions or exclusions

No Comments

No Known Activations