INDEX

Explanations

phrases related to things being off or outside of the norm

oai_token-act-pair · gpt-3.5-turbo

the determiner "the" in various contexts throughout 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

 appreci

-0.68

 cumbers

-0.59

 diplom

-0.59

 expel

-0.58

 noticeably

-0.57

 tremend

-0.57

 Wond

-0.55

 abundantly

-0.54

 perhaps

-0.54

 tonight

-0.53

POSITIVE LOGITS

atre

1.29

ory

1.22

mes

1.14

oret

1.05

ater

1.01

orem

0.94

aters

0.94

ATER

0.93

ories

0.90

Activations Density 0.047%

phrases related to things being off or outside of the norm

the determiner "the" in various contexts throughout the text

No Comments

No Known Activations