INDEX

Explanations

verbs related to reading and writing in a technical context, such as programming or data handling

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "read" and related terms in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

xon

-0.70

 Goodman

-0.66

Ø§ÙĦ

-0.66

Zur

-0.66

olate

-0.60

Ã±o

-0.59

WWF

-0.59

llah

-0.57

 Reeves

-0.57

 Michaels

-0.57

POSITIVE LOGITS

 aloud

1.35

just

1.25

ied

1.18

ying

1.18

 comprehension

1.06

mission

1.01

dress

0.99

mitt

0.98

mitted

0.95

write

0.93

Activations Density 0.059%

verbs related to reading and writing in a technical context, such as programming or data handling

occurrences of the word "read" and related terms in technical contexts

No Comments

No Known Activations