INDEX

Explanations

words related to specific cultural references and proper nouns

oai_token-act-pair · gpt-3.5-turbo

the end of a document or text segment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 corrid

-0.82

 conduc

-0.75

 tremend

-0.75

 conflic

-0.74

Þ

-0.73

 exting

-0.72

Ô

-0.72

 seiz

-0.68

 unnecess

-0.67

 recourse

-0.67

POSITIVE LOGITS

âĦ¢

0.89

 Studios

0.81

 Nights

0.80

Â®

0.77

 Games

0.77

Berry

0.76

 Turtles

0.76

butt

0.76

 extraord

0.75

Games

0.74

Activations Density 0.226%

words related to specific cultural references and proper nouns

the end of a document or text segment

No Comments

No Known Activations