INDEX

Explanations

phrases or terms related to large quantities or size

oai_token-act-pair · gpt-3.5-turbo

references to large concepts, entities, or quantities

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

gently

-0.78

 Jinn

-0.67

 quir

-0.59

mates

-0.58

cers

-0.58

 Orient

-0.57

 Assassins

-0.57

 Behavior

-0.57

 Ghosts

-0.56

 slightest

-0.56

POSITIVE LOGITS

(>

1.12

 conglomer

0.78

occup

0.75

ãĤ¼ãĤ¦ãĤ¹

0.73

ortment

0.69

 è£ıè

0.69

andowski

0.65

uchin

0.65

 undertaking

0.65

 multinational

0.64

Activations Density 0.429%

phrases or terms related to large quantities or size

references to large concepts, entities, or quantities

No Comments

No Known Activations