INDEX

Explanations

phrases that come after the word "by"

oai_token-act-pair · gpt-3.5-turbo

the word "by" in various contexts, indicating authorship or attribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

paren

-0.79

 manif

-0.73

ioned

-0.68

mble

-0.68

hement

-0.66

ĳå£«

-0.66

 torped

-0.66

uality

-0.64

 pains

-0.64

vation

-0.63

POSITIVE LOGITS

 virtue

0.81

laws

0.76

product

0.76

 guiActive

0.70

products

0.68

 Sponsor

0.64

 Lets

0.63

 STATS

0.62

pass

0.61

 Guest

0.59

Activations Density 0.056%

phrases that come after the word "by"

the word "by" in various contexts, indicating authorship or attribution

No Comments

No Known Activations