INDEX

Explanations

the preposition "in" followed by various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in" within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ŀ

-0.68

catentry

-0.65

Ĵ

-0.64

lain

-0.64

ãĥĪ

-0.63

·

-0.61

ãĤ¹

-0.60

ifa

-0.60

Ŀ

-0.60

Ö¼

-0.58

POSITIVE LOGITS

wards

1.15

 unison

1.10

humane

0.99

escap

0.98

animate

0.95

 front

0.93

 vitro

0.93

organic

0.91

bound

0.88

 vain

0.86

Activations Density 0.126%

the preposition "in" followed by various contexts

occurrences of the word "in" within the text

No Comments

No Known Activations