INDEX

Explanations

past tense verbs ending in 'ed'

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "got."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 depiction

-0.66

SPONSORED

-0.63

 confines

-0.61

 Archdemon

-0.61

iege

-0.60

mare

-0.59

deen

-0.58

Ale

-0.58

 Alic

-0.58

allows

-0.57

POSITIVE LOGITS

rid

1.20

cha

0.95

cloneembedreportprint

0.85

ãĥ³ãĤ¸

0.83

DragonMagazine

0.80

acqu

0.76

 acquainted

0.76

terson

0.76

 lucky

0.75

EStream

0.72

Activations Density 0.078%

past tense verbs ending in 'ed'

the repeated use of the word "got."

No Comments

No Known Activations