INDEX

Explanations

the superlatives, particularly the word "Best."

oai_token-act-pair · gpt-3.5-turbo

the word "Best" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

URI

-0.68

nir

-0.66

 balloon

-0.62

 colon

-0.62

 prolifer

-0.62

sectional

-0.61

 iron

-0.61

flies

-0.61

verse

-0.60

wolf

-0.60

POSITIVE LOGITS

 Best

3.48

Best

2.67

 BEST

2.15

best

2.15

 Worst

2.02

 best

1.90

 Favorite

1.46

 Greatest

1.39

worst

1.32

 Better

1.28

Activations Density 0.008%

the superlatives, particularly the word "Best."

the word "Best" in various contexts

No Comments

No Known Activations