INDEX

Explanations

words related to conflicts or arguments

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'c'

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

ĪĴ

-0.92

ãĥĹ

-0.69

 Grateful

-0.67

 contagious

-0.65

 juggling

-0.64

 Yamaha

-0.63

 resil

-0.63

 Tinder

-0.61

 dish

-0.61

 warr

-0.61

POSITIVE LOGITS

ologne

1.24

ursor

1.22

oding

1.21

redits

1.17

ourses

1.14

ortex

1.14

isco

1.14

rossover

1.12

ounters

1.12

ursed

1.10

Activations Density 0.049%

words related to conflicts or arguments

instances of the letter 'c'

No Comments

No Known Activations