INDEX

Explanations

proper nouns or brand names

oai_token-act-pair · gpt-3.5-turbo

the end of the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Ezek

-0.69

eatures

-0.67

 Vaugh

-0.66

 Frie

-0.65

 Adin

-0.64

Els

-0.64

 Gors

-0.62

âĸ¬

-0.62

 Leban

-0.61

uckland

-0.60

POSITIVE LOGITS

Â®

0.66

 apolog

0.64

 celebrates

0.62

 officially

0.61

 quietly

0.60

bender

0.60

 Reloaded

0.60

Wiki

0.58

âĦ¢

0.58

 announces

0.57

Activations Density 0.634%

proper nouns or brand names

the end of the text

No Comments

No Known Activations