INDEX

Explanations

words related to the name "un"

oai_token-act-pair · gpt-3.5-turbo

the prefix "un" indicating negation or reversal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĤ¼

-0.74

INC

-0.69

 Madden

-0.62

 elig

-0.62

Ö¼

-0.61

 abiding

-0.60

 refres

-0.60

 loopholes

-0.58

 Garfield

-0.57

 watered

-0.57

POSITIVE LOGITS

culus

1.32

nels

1.31

nel

1.30

geon

1.26

culosis

1.25

geons

1.22

cheon

1.19

uchs

1.14

nery

1.14

kered

1.10

Activations Density 0.043%

words related to the name "un"

the prefix "un" indicating negation or reversal

No Comments

No Known Activations