INDEX

Explanations

first-person singular pronouns and verbs indicating thought or speculation

oai_token-act-pair · gpt-3.5-turbo

pronouns that indicate self-reference, particularly "I."

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

 Walton

-0.64

ources

-0.63

rising

-0.62

 Clancy

-0.61

tions

-0.61

 Uriel

-0.61

 Pearson

-0.60

 Roose

-0.59

psons

-0.59

 Thrones

-0.59

POSITIVE LOGITS

'm

1.49

am

1.05

've

1.02

verson

0.99

RL

0.96

ANA

0.93

'll

0.91

MAX

0.90

 guess

0.88

 myself

0.87

Activations Density 0.171%

first-person singular pronouns and verbs indicating thought or speculation

pronouns that indicate self-reference, particularly "I."

No Comments

No Known Activations